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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rationale
    -0.08
     수행
    -0.08
     речи
    -0.08
    推
    -0.08
    क्षा
    -0.07
     Bell
    -0.07
     relève
    -0.07
    .Header
    -0.07
    람
    -0.07
    bericht
    -0.07
    POSITIVE LOGITS
     hipert
    0.09
     tribut
    0.09
     silver
    0.08
     Tribut
    0.08
    silver
    0.08
     california
    0.08
     testosterone
    0.08
     ngob
    0.08
    _timezone
    0.08
     hardwood
    0.08
    Act Density 0.004%

    No Known Activations