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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *self
    -0.07
    ...")↵
    -0.07
     awake
    -0.07
    -shift
    -0.07
     zou
    -0.06
     twenty
    -0.06
    steps
    -0.06
     профессиональ
    -0.06
     accompanied
    -0.06
    nine
    -0.06
    POSITIVE LOGITS
    ئيس
    0.06
    家庭
    0.06
     radix
    0.06
     CPR
    0.06
    корист
    0.06
    AB
    0.06
    Brazil
    0.06
    ?(
    0.06
     candies
    0.06
    pData
    0.06
    Act Density 0.000%

    No Known Activations