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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gold
    -0.07
    _FP
    -0.06
    _stderr
    -0.06
    _required
    -0.06
    _ACC
    -0.06
     Altın
    -0.06
    -text
    -0.06
    SMS
    -0.06
    estival
    -0.06
     edilen
    -0.06
    POSITIVE LOGITS
     may
    0.07
     Bài
    0.07
     admission
    0.07
     errores
    0.06
    맛
    0.06
     hypotheses
    0.06
     Deputy
    0.06
     contraception
    0.06
     статьи
    0.06
     fabrics
    0.06
    Act Density 0.007%

    No Known Activations