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

    Neuronpedia

    INDEX
    Explanations

    equivalent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .');
    -0.08
    -grey
    -0.07
     الترك
    -0.07
    reason
    -0.07
    (rule
    -0.07
     Designer
    -0.07
     Drop
    -0.07
    参考
    -0.06
     Work
    -0.06
     inspire
    -0.06
    POSITIVE LOGITS
     straps
    0.08
     shorthand
    0.07
    欧冠
    0.07
     equivalent
    0.07
    袤
    0.07
     hükümet
    0.06
    쁨
    0.06
    夥
    0.06
     أبريل
    0.06
    领导干部
    0.06
    Act Density 0.010%

    No Known Activations