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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate uncertainty or lack of clarity

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

    Questions

    np_acts-logits-general · gemini-2.0-flash

    asking how, what, or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setContentView
    -0.52
     _$
    -0.48
     inhibition
    -0.46
    せよ
    -0.45
     $("<
    -0.45
    resso
    -0.45
    issan
    -0.45
    的一次
    -0.44
    rilla
    -0.44
     Rod
    -0.43
    POSITIVE LOGITS
     how
    1.46
     why
    1.26
     what
    1.20
     whether
    1.07
     bagaimana
    0.87
    how
    0.87
     cómo
    0.86
    why
    0.85
     hvordan
    0.82
     cuál
    0.81
    Act Density 0.404%

    No Known Activations