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

    Neuronpedia

    INDEX
    Explanations

    Double-strand breaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helps
    -0.08
    bug
    -0.07
    .Red
    -0.07
    灾
    -0.07
    facebook
    -0.07
    反
    -0.07
     pagan
    -0.07
    
↵
    -0.07
    返回
    -0.07
    三季度
    -0.06
    POSITIVE LOGITS
     vile
    0.07
     Diy
    0.07
     Lexer
    0.07
     מעל
    0.07
    _old
    0.07
    桥梁
    0.07
    胆固醇
    0.07
     mówi
    0.06
    _cap
    0.06
    oice
    0.06
    Act Density 0.004%

    No Known Activations