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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nex
    -0.07
     nach
    -0.07
    orre
    -0.07
    ЛЬ
    -0.07
    apg
    -0.06
     KING
    -0.06
     hometown
    -0.06
     trumpet
    -0.06
    obre
    -0.06
    ATCH
    -0.06
    POSITIVE LOGITS
    layıcı
    0.07
     congestion
    0.07
    _checkpoint
    0.07
    Pattern
    0.06
    _performance
    0.06
     家
    0.06
    ModelCreating
    0.06
    ‚
    0.06
    .urlencoded
    0.06
    _firstname
    0.06
    Act Density 0.000%

    No Known Activations