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

    Neuronpedia

    INDEX
    Explanations

    verification portal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posible
    0.57
     posibles
    0.54
     &&
    0.52
    hd
    0.50
     possíveis
    0.47
     possibles
    0.46
     siyah
    0.46
    unwrap
    0.45
     possível
    0.44
     deprecated
    0.44
    POSITIVE LOGITS
    September
    0.42
    ായക
    0.41
    OUTH
    0.39
     mornings
    0.38
     September
    0.38
    దు
    0.38
    issanti
    0.38
    庆祝
    0.38
    Ohio
    0.37
    ക്ക
    0.37
    Act Density 0.000%

    No Known Activations