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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    高三
    -0.08
     prend
    -0.07
    HX
    -0.07
     JComboBox
    -0.07
    Drv
    -0.06
    content
    -0.06
    ローン
    -0.06
    ZX
    -0.06
    Serialization
    -0.06
     motivo
    -0.06
    POSITIVE LOGITS
     Frames
    0.07
    .isOpen
    0.07
     ratio
    0.07
    وب
    0.07
    .popup
    0.07
     fputs
    0.07
     ogó
    0.07
    .bucket
    0.06
     omega
    0.06
    wide
    0.06
    Act Density 0.017%

    No Known Activations