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

    Neuronpedia

    INDEX
    Explanations

    revision

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    踝
    -0.07
    忡
    -0.07
    塅
    -0.07
    而又
    -0.07
     ترك
    -0.07
    弈
    -0.07
    憧
    -0.07
    槐
    -0.07
    kont
    -0.06
    嬗
    -0.06
    POSITIVE LOGITS
     verification
    0.07
    #######
    0.07
     renewal
    0.07
     Alexandria
    0.07
     slashing
    0.07
     수
    0.07
    有名
    0.07
     biblical
    0.07
     allege
    0.07
     Hide
    0.06
    Act Density 0.000%

    No Known Activations