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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nid
    -0.07
     MILF
    -0.07
     OSS
    -0.06
     Scaffold
    -0.06
    Central
    -0.06
    .intent
    -0.06
     Sakura
    -0.06
    .TypeString
    -0.06
    Military
    -0.06
    >ID
    -0.06
    POSITIVE LOGITS
     et
    0.07
     wrought
    0.07
     पढ
    0.06
    /null
    0.06
     hton
    0.06
    ision
    0.06
    rot
    0.06
     extraordinarily
    0.06
     disregard
    0.06
     ев
    0.06
    Act Density 0.001%

    No Known Activations