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

    Neuronpedia

    INDEX
    Explanations

    Code and instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     жен
    -0.07
     Loan
    -0.07
     Brave
    -0.07
     FLOAT
    -0.07
     Verd
    -0.07
     Carly
    -0.07
    .as
    -0.07
    cou
    -0.07
    Mrs
    -0.07
    .thread
    -0.06
    POSITIVE LOGITS
    0.08
    ߨ
    0.07
    controls
    0.07
    𝙠
    0.07
    书法家
    0.07
    获得了
    0.07
    坻
    0.07
    𝓱
    0.06
    估计
    0.06
    '},
    0.06
    Act Density 0.002%

    No Known Activations