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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peaks
    -0.07
    ACIÓN
    -0.07
     svět
    -0.06
    Writes
    -0.06
     ngồi
    -0.06
     últ
    -0.06
    :href
    -0.06
    én
    -0.06
    _MODULES
    -0.06
     Leaves
    -0.06
    POSITIVE LOGITS
    긴
    0.06
     ew
    0.06
    exemple
    0.06
    dın
    0.06
    คณะ
    0.06
    /storage
    0.06
    -
↵
    0.06
    有
    0.06
     din
    0.06
    -ending
    0.06
    Act Density 0.011%

    No Known Activations