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

    Neuronpedia

    INDEX
    Explanations

    local topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Light
    -0.07
     Fel
    -0.06
     natural
    -0.06
     marrow
    -0.06
    armacy
    -0.06
     injuries
    -0.06
     threading
    -0.06
     liên
    -0.06
    (build
    -0.06
     اج
    -0.06
    POSITIVE LOGITS
    ibil
    0.07
    GORITH
    0.07
     Brussels
    0.06
     Cumhurbaş
    0.06
    ス
    0.06
    ">{{$
    0.06
    _TRAIN
    0.06
    ś
    0.06
     Durch
    0.06
     равно
    0.06
    Act Density 0.081%

    No Known Activations