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

    Neuronpedia

    INDEX
    Explanations

    Will followed by names or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    maybe
    0.41
     in
    0.39
     실제
    0.39
     можливо
    0.38
    可能有
    0.38
     Throwable
    0.37
    //
    0.37
    sensitivity
    0.36
     sensitivity
    0.36
    可能是
    0.36
    POSITIVE LOGITS
     gladly
    0.63
     NEVER
    0.53
     never
    0.52
    IAMS
    0.50
     niemals
    0.48
     jamás
    0.46
    amette
    0.46
     WILL
    0.46
     Never
    0.45
     abide
    0.45
    Act Density 0.003%

    No Known Activations