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

    Neuronpedia

    INDEX
    Explanations

    instances of technical specifications and related descriptions

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

    shown in figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.79
     queſta
    -0.75
    ſelf
    -0.75
    хьтан
    -0.74
    ſelves
    -0.73
     صوتيه
    -0.73
    extAlignment
    -0.72
    IntOverflow
    -0.72
    ChildScrollView
    -0.71
    новништво
    -0.71
    POSITIVE LOGITS
     did
    0.38
     stage
    0.35
    ar
    0.32
     tutorial
    0.32
     Tutorial
    0.31
     czerwony
    0.31
     again
    0.31
     next
    0.30
     Reg
    0.30
     Fee
    0.30
    Act Density 0.224%

    No Known Activations