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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diferencia
    -0.08
    콰
    -0.07
     cyan
    -0.07
     חר
    -0.07
     Flores
    -0.07
    	Title
    -0.07
     бо
    -0.07
     llegar
    -0.07
     credential
    -0.07
     PLUGIN
    -0.07
    POSITIVE LOGITS
    Roll
    0.07
    cr
    0.07
    记者表示
    0.07
    鼓
    0.07
     saf
    0.07
    _sp
    0.07
     möglich
    0.07
     flotation
    0.07
    	part
    0.07
     Recorded
    0.07
    Act Density 0.000%

    No Known Activations