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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    not
    0.75
     sapere
    0.70
     not
    0.68
     அதிகரி
    0.63
    ा
    0.63
    ノ
    0.62
    चं
    0.61
    Ultr
    0.61
    NOT
    0.60
    cent
    0.59
    POSITIVE LOGITS
    Possible
    0.89
     possible
    0.87
     Possible
    0.83
     POSSIBLE
    0.78
    possible
    0.74
     posible
    0.74
     possíveis
    0.74
     возмо
    0.73
     kinds
    0.72
     möglichen
    0.72
    Act Density 0.119%

    No Known Activations