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

    Neuronpedia

    INDEX
    Explanations

    Change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Presidential
    -0.07
     induces
    -0.06
     Ag
    -0.06
    Под
    -0.06
     nông
    -0.06
    amples
    -0.06
    向东
    -0.06
    正当
    -0.06
    ammed
    -0.06
     electric
    -0.06
    POSITIVE LOGITS
    🍇
    0.07
     juni
    0.07
    收官
    0.07
    📂
    0.07
    صدق
    0.07
     chk
    0.07
    区域内
    0.07
     allowable
    0.07
    하실
    0.07
    ивание
    0.07
    Act Density 0.204%

    No Known Activations