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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tiği
    -0.07
    osp
    -0.07
    .rep
    -0.06
    OLUMNS
    -0.06
     pré
    -0.06
     Speaking
    -0.06
    encoder
    -0.06
     forth
    -0.06
    quared
    -0.06
    小学
    -0.05
    POSITIVE LOGITS
    ้าส
    0.07
    ukt
    0.07
     Actions
    0.07
    .management
    0.07
     Cambridge
    0.06
     indoor
    0.06
     Link
    0.06
     differences
    0.06
     Smith
    0.06
    aravel
    0.06
    Act Density 0.008%

    No Known Activations