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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RADIO
    -0.07
    _proc
    -0.07
    Callbacks
    -0.07
    yı
    -0.07
    District
    -0.06
    /document
    -0.06
    Owner
    -0.06
     الاع
    -0.06
     Fun
    -0.06
    pear
    -0.06
    POSITIVE LOGITS
    实现
    0.06
     Watts
    0.06
    bos
    0.06
     drift
    0.06
     آلة
    0.06
     Poh
    0.06
     succinct
    0.06
     drib
    0.06
     (--
    0.06
    damage
    0.06
    Act Density 0.029%

    No Known Activations