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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    алась
    -0.07
     chảy
    -0.07
     Therefore
    -0.07
    aval
    -0.07
     Shaft
    -0.06
     жиз
    -0.06
    ו
    -0.06
     Afterwards
    -0.06
     stakeholders
    -0.06
    ุต
    -0.06
    POSITIVE LOGITS
     fr
    0.07
    <int
    0.07
    ombie
    0.07
    [str
    0.06
     Dinner
    0.06
     inland
    0.06
     filib
    0.06
     대
    0.06
     To
    0.06
     VIR
    0.06
    Act Density 0.026%

    No Known Activations