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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hostname
    -0.08
    ethyl
    -0.07
    /cli
    -0.07
     ctr
    -0.07
     вещ
    -0.07
    attr
    -0.07
     dequeueReusableCell
    -0.07
     breastfeeding
    -0.07
     bb
    -0.06
    只是
    -0.06
    POSITIVE LOGITS
     Larson
    0.07
    _VER
    0.07
     Forms
    0.07
     forms
    0.06
    amaz
    0.06
    -an
    0.06
     glazed
    0.06
     sidew
    0.06
    _V
    0.06
    reds
    0.06
    Act Density 0.009%

    No Known Activations