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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Fragment
    -0.07
    EGIN
    -0.07
    OG
    -0.06
    _PROTO
    -0.06
    edad
    -0.06
    _superuser
    -0.06
     NSLog
    -0.06
     Paramount
    -0.06
    avier
    -0.06
    ]int
    -0.06
    POSITIVE LOGITS
    /P
    0.06
     takım
    0.06
     conta
    0.06
     rất
    0.06
     fortunate
    0.06
    Within
    0.06
    些
    0.06
     survivors
    0.06
     disgu
    0.06
     farklı
    0.06
    Act Density 0.533%

    No Known Activations