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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sind
    -0.07
     mime
    -0.07
     flight
    -0.07
     Fly
    -0.07
    NL
    -0.07
    穿越
    -0.07
     tls
    -0.07
    ght
    -0.07
    (active
    -0.07
     tangled
    -0.06
    POSITIVE LOGITS
    Autoresizing
    0.07
     الروسي
    0.07
    에
    0.07
    ografia
    0.07
     unilateral
    0.07
    lemma
    0.07
     السورية
    0.07
    iad
    0.07
    öğretim
    0.06
     pla
    0.06
    Act Density 0.000%

    No Known Activations