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

    Neuronpedia

    INDEX
    Explanations

    AdSense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    サイ
    -0.08
    笪
    -0.08
    תיב
    -0.07
     Kay
    -0.06
     Assessment
    -0.06
     Wass
    -0.06
     приним
    -0.06
     berhasil
    -0.06
    -di
    -0.06
    防汛
    -0.06
    POSITIVE LOGITS
    _with
    0.08
     shapes
    0.07
     commitments
    0.07
    lico
    0.07
    需求
    0.07
     interruptions
    0.07
     windows
    0.07
    (batch
    0.07
     pretending
    0.07
    .Roles
    0.07
    Act Density 0.002%

    No Known Activations