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

    Neuronpedia

    INDEX
    Explanations

    inventory ordering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flour
    -0.08
     تخ
    -0.08
     прож
    -0.08
     ketchup
    -0.08
     vow
    -0.08
     впечат
    -0.07
     lived
    -0.07
    avier
    -0.07
    ории
    -0.07
     vape
    -0.07
    POSITIVE LOGITS
    Triggered
    0.10
     triggered
    0.10
     triggers
    0.09
    _THRESHOLD
    0.09
    =M
    0.08
     corrective
    0.08
    Threshold
    0.08
    Automatic
    0.08
     automático
    0.08
     replen
    0.08
    Act Density 0.003%

    No Known Activations