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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ilaç
    -0.08
    𝕦
    -0.07
    Exports
    -0.07
    大蒜
    -0.07
    村子
    -0.07
    艿
    -0.07
     الأسهم
    -0.07
    哭了
    -0.07
    修士
    -0.07
     süre
    -0.07
    POSITIVE LOGITS
     없
    0.07
    ┇
    0.07
    ].
    0.06
    سكن
    0.06
    _from
    0.06
    シェ
    0.06
     symbol
    0.06
     honey
    0.06
    _system
    0.06
    conscious
    0.06
    Act Density 0.000%

    No Known Activations