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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ∀
    -0.06
    achment
    -0.06
     рев
    -0.06
     compatible
    -0.06
    试
    -0.06
    .dd
    -0.06
     дис
    -0.06
     �
    -0.06
    дав
    -0.06
    irmware
    -0.06
    POSITIVE LOGITS
    =""/>↵
    0.07
    {k
    0.07
    _spot
    0.06
     Gulf
    0.06
     ку
    0.06
     */
↵
    0.06
     reactor
    0.06
     revolving
    0.06
     kı
    0.05
    )*/↵
    0.05
    Act Density 0.042%

    No Known Activations