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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     courtesy
    -0.06
     pouring
    -0.06
     iy
    -0.06
    ерк
    -0.06
     importantes
    -0.06
     moy
    -0.06
     inplace
    -0.06
    ceptar
    -0.06
    ')}}"
    -0.06
    pees
    -0.06
    POSITIVE LOGITS
     not
    0.07
    agedList
    0.07
    _TICK
    0.07
    构
    0.07
    .Feed
    0.07
     �
    0.07
    isease
    0.06
     prom
    0.06
     focusing
    0.06
     コ
    0.06
    Act Density 0.008%

    No Known Activations