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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cardio
    -0.08
     builds
    -0.07
    _allocate
    -0.07
     noticias
    -0.07
     grind
    -0.07
    傩
    -0.07
    Tue
    -0.07
     yalnız
    -0.07
     sieht
    -0.06
     dislikes
    -0.06
    POSITIVE LOGITS
    �
    0.07
     presenter
    0.06
    交织
    0.06
    >{!!
    0.06
    ＆
    0.06
    /year
    0.06
    Most
    0.06
    upper
    0.06
     limits
    0.06
     (*
    0.06
    Act Density 0.009%

    No Known Activations