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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zeigt
    -0.06
    ',//
    -0.06
    792
    -0.05
    _SW
    -0.05
    љ
    -0.05
     comun
    -0.05
     αρι
    -0.05
    .Pattern
    -0.05
    Index
    -0.05
     мод
    -0.05
    POSITIVE LOGITS
    Configure
    0.07
    _interface
    0.07
     ftp
    0.07
     Tatto
    0.06
     Executive
    0.06
    ões
    0.06
    Iss
    0.06
     ballpark
    0.06
    AGED
    0.06
     fa
    0.06
    Act Density 0.001%

    No Known Activations