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

    Neuronpedia

    INDEX
    Explanations

    /of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ульта
    -0.07
     أر
    -0.06
     заліз
    -0.06
     بسته
    -0.06
     зуб
    -0.06
     confines
    -0.06
    �
    -0.06
    Dans
    -0.06
     poj
    -0.06
     rời
    -0.06
    POSITIVE LOGITS
     necessarily
    0.07
     REF
    0.07
    .basename
    0.06
     HH
    0.06
     Marxism
    0.06
    params
    0.06
     Marshall
    0.06
     Synthetic
    0.06
    _cleanup
    0.06
    -array
    0.06
    Act Density 0.002%

    No Known Activations