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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .unit
    -0.07
     requ
    -0.06
    -media
    -0.06
     sik
    -0.06
    itionally
    -0.06
     inp
    -0.06
    ấp
    -0.06
    たら
    -0.06
     avail
    -0.06
     following
    -0.06
    POSITIVE LOGITS
     Goku
    0.07
    iloc
    0.07
    EEP
    0.06
     TT
    0.06
    EFF
    0.06
     Copy
    0.06
     (;;)
    0.06
    (getClass
    0.06
     يونيو
    0.06
     баж
    0.06
    Act Density 0.102%

    No Known Activations