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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heav
    -0.06
     ス
    -0.06
    'R
    -0.06
    ゝ
    -0.06
    guest
    -0.06
     stále
    -0.06
     gim
    -0.06
    ентів
    -0.06
     oran
    -0.06
    acency
    -0.06
    POSITIVE LOGITS
    _supply
    0.07
    braska
    0.07
     заст
    0.07
     Slovak
    0.06
     віз
    0.06
    營
    0.06
    �
    0.06
     zkou
    0.06
    創
    0.06
     TObject
    0.06
    Act Density 0.001%

    No Known Activations