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

    Neuronpedia

    INDEX
    Explanations

    US states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uri
    -0.07
    ших
    -0.07
    Este
    -0.07
    alım
    -0.07
    拔
    -0.07
    exact
    -0.07
    (dto
    -0.06
    circ
    -0.06
    К
    -0.06
    Join
    -0.06
    POSITIVE LOGITS
     usuário
    0.06
     운동
    0.06
     inconsistencies
    0.06
     Geile
    0.06
    _br
    0.06
     字
    0.06
     Persian
    0.06
     QMessageBox
    0.06
    érience
    0.06
     mechanics
    0.06
    Act Density 0.046%

    No Known Activations