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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zych
    -0.07
    忍
    -0.06
    とか
    -0.06
    ammable
    -0.06
     holds
    -0.06
    upaten
    -0.06
    �
    -0.06
    "How
    -0.06
    wie
    -0.06
     canceled
    -0.06
    POSITIVE LOGITS
    -sign
    0.07
     연
    0.07
    (single
    0.07
    _char
    0.07
     trigger
    0.07
     $"
    0.07
    ilitary
    0.07
     clothing
    0.07
     boots
    0.06
    lice
    0.06
    Act Density 0.000%

    No Known Activations