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

    Neuronpedia

    INDEX
    Explanations

    colonial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    湛
    -0.07
    À
    -0.07
     Jake
    -0.07
    abyrinth
    -0.07
    ricular
    -0.06
    essment
    -0.06
     À
    -0.06
    -US
    -0.06
     priced
    -0.06
    长得
    -0.06
    POSITIVE LOGITS
    .mdl
    0.07
    嬖
    0.07
    发明
    0.07
     İslam
    0.07
    .labelControl
    0.07
    𝙢
    0.07
    .manual
    0.06
    itbart
    0.06
     cloak
    0.06
    文學
    0.06
    Act Density 0.007%

    No Known Activations