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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Headers
    -0.07
     كس
    -0.07
    (crate
    -0.07
     confidently
    -0.06
     Wars
    -0.06
     özellikle
    -0.06
    Ê
    -0.06
    acher
    -0.06
     IB
    -0.06
     Pek
    -0.06
    POSITIVE LOGITS
     imposes
    0.07
    Asset
    0.06
     __________________________________
    0.06
    andum
    0.06
     فی
    0.06
    PATCH
    0.06
     Corporate
    0.06
     xsi
    0.06
     Salah
    0.06
    oracle
    0.06
    Act Density 0.007%

    No Known Activations