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

    Neuronpedia

    INDEX
    Explanations

    frequency range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astic
    1.11
    ção
    1.00
    izarea
    0.95
    isti
    0.94
    fø
    0.94
    isiä
    0.94
    anging
    0.91
    istet
    0.89
    жении
    0.86
    ıkları
    0.85
    POSITIVE LOGITS
    6
    1.99
    7
    1.98
    3
    1.96
    Moscow
    1.81
    5
    1.80
    9
    1.80
    8
    1.79
    4
    1.76
    學院
    1.75
    Royal
    1.75
    Act Density 0.123%

    No Known Activations