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

    Neuronpedia

    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attributes
    -0.08
    שינוי
    -0.07
    iotic
    -0.06
    “One
    -0.06
    InterruptedException
    -0.06
     plotted
    -0.06
    بيد
    -0.06
     such
    -0.06
    pipes
    -0.06
    'b
    -0.06
    POSITIVE LOGITS
    叻
    0.07
    _between
    0.07
     Franklin
    0.07
     watchers
    0.07
     draft
    0.07
     Telephone
    0.07
    老旧
    0.07
    デート
    0.07
    窄
    0.07
    遣
    0.06
    Act Density 0.003%

    No Known Activations