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

    Neuronpedia

    INDEX
    Explanations

    Theoretical analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }}"
    -0.06
    ivel
    -0.06
    ِّ
    -0.06
     οπο
    -0.06
     racket
    -0.06
    _NET
    -0.06
    Clr
    -0.06
    classCallCheck
    -0.06
    Os
    -0.06
    -------
    -0.06
    POSITIVE LOGITS
     Assistant
    0.07
     Killing
    0.07
     причины
    0.06
    wifi
    0.06
     traitement
    0.06
    แฟ
    0.06
     रन
    0.06
    .cgi
    0.06
     khí
    0.06
    scaling
    0.06
    Act Density 0.049%

    No Known Activations