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

    Neuronpedia

    INDEX
    Explanations

    say "Exp"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Urb
    -0.07
     Still
    -0.07
    موا
    -0.07
     tougher
    -0.07
     Entertainment
    -0.07
     multinational
    -0.07
    [t
    -0.06
    .signup
    -0.06
    uards
    -0.06
    莴
    -0.06
    POSITIVE LOGITS
    止损
    0.07
    $request
    0.07
    丛
    0.07
    ׳
    0.07
    eced
    0.07
     النبي
    0.07
    权威
    0.07
     values
    0.06
    (j
    0.06
    quierda
    0.06
    Act Density 0.002%

    No Known Activations