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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izieren
    -0.08
    Detalle
    -0.07
    ститу
    -0.07
     formular
    -0.07
    astu
    -0.07
    پور
    -0.07
     talking
    -0.07
    ust
    -0.07
    -tax
    -0.07
    acidad
    -0.07
    POSITIVE LOGITS
     orchestra
    0.08
     resa
    0.08
     oorspronk
    0.07
     rozpoc
    0.07
     fuite
    0.07
    #elif
    0.07
     Espírito
    0.07
     nessa
    0.07
     originalmente
    0.07
    RESA
    0.07
    Act Density 0.000%

    No Known Activations