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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кин
    -0.06
    theon
    -0.06
    kick
    -0.06
    masters
    -0.06
     recounts
    -0.06
    goods
    -0.06
    üssen
    -0.06
    elter
    -0.06
     хто
    -0.05
    close
    -0.05
    POSITIVE LOGITS
     版
    0.07
     territor
    0.07
    _testing
    0.07
    _embedding
    0.07
     합
    0.06
    .setTitle
    0.06
    (Enum
    0.06
    oi
    0.06
    <>("
    0.06
    _emb
    0.06
    Act Density 0.000%

    No Known Activations