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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .connector
    -0.07
    规
    -0.06
    .addObserver
    -0.06
    .getInteger
    -0.06
    呼
    -0.06
    Foto
    -0.06
    اری
    -0.06
    DetailsService
    -0.06
    fra
    -0.06
    ighborhood
    -0.06
    POSITIVE LOGITS
    �
    0.07
     heals
    0.06
    .buf
    0.06
    MT
    0.06
     convert
    0.06
     sistemi
    0.06
    .Tree
    0.06
     tries
    0.06
     transmitting
    0.06
     cab
    0.06
    Act Density 0.000%

    No Known Activations