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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     removed
    -0.07
     Loot
    -0.07
    OT
    -0.07
     пля
    -0.06
     orphan
    -0.06
     removing
    -0.06
    Subject
    -0.06
    submit
    -0.06
     certificate
    -0.06
     Morocco
    -0.06
    POSITIVE LOGITS
     कहन
    0.07
    萬
    0.07
    acağını
    0.07
     मण
    0.07
    :::::|
    0.07
    інь
    0.07
     yapmak
    0.06
     :.|
    0.06
    emplate
    0.06
    :Any
    0.06
    Act Density 0.005%

    No Known Activations