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

    Neuronpedia

    INDEX
    Explanations

    dot commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脑袋
    -0.07
     slowdown
    -0.07
    쫄
    -0.07
    озвращ
    -0.07
    湴
    -0.07
     zwe
    -0.07
    עק
    -0.07
     interf
    -0.07
    etre
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     <↵
    0.07
    工资
    0.07
     compromises
    0.07
    𝘨
    0.07
     الع
    0.07
     matrimon
    0.07
    ++;
↵
    0.07
     Cor
    0.06
    ["
    0.06
    主治
    0.06
    Act Density 0.021%

    No Known Activations