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

    Neuronpedia

    INDEX
    Explanations

    links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    V
    1.09
    Tapi
    0.94
    F
    0.93
    B
    0.91
    P
    0.91
    вет
    0.89
    H
    0.87
    S
    0.82
    K
    0.81
    O
    0.79
    POSITIVE LOGITS
     Faktoren
    0.98
     kommt
    0.93
     okula
    0.93
    estinal
    0.93
    बिनेट
    0.91
     sucht
    0.91
     ہوں
    0.91
     otrzyma
    0.91
    酛
    0.90
     accanto
    0.88
    Act Density 0.003%

    No Known Activations