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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inez
    -0.08
     Until
    -0.07
    аря
    -0.07
    ust
    -0.07
    �
    -0.06
    _EXCEPTION
    -0.06
    yz
    -0.06
     TN
    -0.06
     мереж
    -0.06
    undles
    -0.06
    POSITIVE LOGITS
    *f
    0.07
    .Full
    0.06
     cj
    0.06
    anime
    0.06
     severely
    0.06
     nebu
    0.06
     bf
    0.06
     Hermes
    0.06
     Sponsored
    0.06
    0.06
    Act Density 0.018%

    No Known Activations