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

    Neuronpedia

    INDEX
    Explanations

    file handles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ров
    -0.07
    包括
    -0.07
     trillion
    -0.06
    ụn
    -0.06
    roman
    -0.06
    angular
    -0.06
    _favorite
    -0.06
    ,String
    -0.06
    .BooleanField
    -0.06
    ravel
    -0.06
    POSITIVE LOGITS
     ・
    0.07
     dla
    0.06
    }.
    0.06
     autoFocus
    0.06
     Piper
    0.06
     Projectile
    0.06
    duk
    0.06
     esk
    0.06
    За
    0.06
     thr
    0.06
    Act Density 0.022%

    No Known Activations