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

    Neuronpedia

    INDEX
    Explanations

    starting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compart
    -0.07
    vět
    -0.06
    쇼
    -0.06
     �
    -0.06
    يلاد
    -0.06
    руш
    -0.06
    DateString
    -0.06
    貨
    -0.06
    �
    -0.06
    RSA
    -0.06
    POSITIVE LOGITS
    fill
    0.07
     أمريكي
    0.07
    lambda
    0.07
     dep
    0.07
     Starting
    0.07
    .textField
    0.06
     beginning
    0.06
    upyter
    0.06
    +",
    0.06
     contract
    0.06
    Act Density 0.004%

    No Known Activations