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

    Neuronpedia

    INDEX
    Explanations

    code imports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     though
    -0.08
    aution
    -0.07
    ेको
    -0.07
    jší
    -0.07
    ाउनु
    -0.07
     České
    -0.07
    nge
    -0.07
    necedor
    -0.07
    acters
    -0.07
     specifies
    -0.07
    POSITIVE LOGITS
     initiated
    0.10
     пог
    0.09
    Initi
    0.09
     мастац
    0.08
     തേ
    0.08
     ప్రారంభ
    0.08
     Initi
    0.08
     दौर
    0.08
     rozpoc
    0.08
     dokon
    0.08
    Act Density 0.003%

    No Known Activations