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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WHITE
    -0.08
    htt
    -0.07
     dildo
    -0.07
    aises
    -0.07
    ्रण
    -0.07
    cert
    -0.07
     PIN
    -0.07
    \Model
    -0.06
    _IRQHandler
    -0.06
    reement
    -0.06
    POSITIVE LOGITS
    不足
    0.07
     uh
    0.07
    `=
    0.07
     multimedia
    0.07
     высокой
    0.06
     chắn
    0.06
    ----------------------------------------------------------------------------
    0.06
    DATABASE
    0.06
     Flexible
    0.06
    (DEFAULT
    0.06
    Act Density 0.005%

    No Known Activations