Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of technical and procedural information related to software and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words or phrases suggesting "ease" or "simplicity"

    np_acts-logits-general · gemini-2.0-flash

    ease and simplicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tfsi
    -0.69
     myſelf
    -0.66
     Majefty
    -0.66
     cdti
    -0.63
     crdi
    -0.59
    %";
    -0.59
    хьтан
    -0.58
    AppRoutingModule
    -0.56
     betweenstory
    -0.55
    aarrggbb
    -0.55
    POSITIVE LOGITS
     easy
    3.34
    easy
    2.95
    Easy
    2.79
     Easy
    2.78
     EASY
    2.62
     easier
    2.56
     simple
    2.45
     easiest
    2.37
     easily
    2.36
    EASY
    2.35
    Act Density 0.717%

    No Known Activations