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

    Neuronpedia

    INDEX
    Explanations

    isms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SU
    -0.07
     då
    -0.07
     factor
    -0.06
     меропри
    -0.06
    .COL
    -0.06
    .spi
    -0.06
     component
    -0.06
     �
    -0.06
     позд
    -0.06
     adm
    -0.06
    POSITIVE LOGITS
    _supp
    0.07
    .STATUS
    0.07
    _WHITE
    0.06
    Friday
    0.06
    0.06
     Remed
    0.06
    Verifier
    0.06
    hte
    0.06
    _DT
    0.06
    >{$
    0.06
    Act Density 0.000%

    No Known Activations