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
    롹
    -0.07
    ☦
    -0.07
    ặp
    -0.07
    纾
    -0.07
     개최
    -0.07
    metic
    -0.06
    תופ
    -0.06
    짚
    -0.06
    Areas
    -0.06
    撄
    -0.06
    POSITIVE LOGITS
    _LINK
    0.08
    (float
    0.07
    .Future
    0.07
    /kg
    0.07
     Disney
    0.07
    minute
    0.07
    远程
    0.07
     характеристик
    0.07
    ANGE
    0.07
     sim
    0.07
    Act Density 0.001%

    No Known Activations