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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系
    -0.08
    Sets
    -0.08
    ерин
    -0.07
    amics
    -0.07
     těch
    -0.06
    .tabs
    -0.06
     jewish
    -0.06
    Iran
    -0.06
    npj
    -0.06
    ,UnityEngine
    -0.06
    POSITIVE LOGITS
    Emer
    0.07
     başk
    0.07
    AppState
    0.06
     öldür
    0.06
    utherford
    0.06
    ıklı
    0.06
     obstruction
    0.06
    COMMON
    0.06
    POR
    0.06
     Eugene
    0.06
    Act Density 0.008%

    No Known Activations