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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _flip
    -0.06
     boxed
    -0.06
     diferente
    -0.06
     homes
    -0.06
     IUser
    -0.06
    .colors
    -0.06
    -vector
    -0.06
    _points
    -0.06
    .daily
    -0.06
    soc
    -0.06
    POSITIVE LOGITS
    دى
    0.07
     thọ
    0.07
     $↵
    0.06
     علم
    0.06
    Cerrar
    0.06
     исполн
    0.06
     curly
    0.06
     işte
    0.06
     eoq
    0.06
     CUT
    0.06
    Act Density 0.069%

    No Known Activations