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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hott
    -0.07
     şek
    -0.07
    .card
    -0.07
    _pres
    -0.06
    -sc
    -0.06
     Frankfurt
    -0.06
     Parad
    -0.06
    规定
    -0.06
    �
    -0.06
     às
    -0.06
    POSITIVE LOGITS
     духов
    0.06
    ζί
    0.06
    arium
    0.06
    .checkBox
    0.06
    DIR
    0.06
    dictionary
    0.06
    EF
    0.06
     scattering
    0.06
    nie
    0.06
    .help
    0.06
    Act Density 0.006%

    No Known Activations