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

    Neuronpedia

    INDEX
    Explanations

    depression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pepper
    -0.07
     annoyed
    -0.07
     hazard
    -0.07
    _visible
    -0.06
    ゃ
    -0.06
    Rp
    -0.06
    utar
    -0.06
    :
↵
    -0.06
    čer
    -0.06
     dzi
    -0.06
    POSITIVE LOGITS
     다양한
    0.07
    .intValue
    0.07
    غراف
    0.07
    >'.↵
    0.06
     المغ
    0.06
    .Mult
    0.06
     Ấn
    0.06
     fortress
    0.06
     گرف
    0.06
    ิงห
    0.06
    Act Density 0.068%

    No Known Activations