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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তি
    0.70
    $-
    0.69
    $-(
    0.67
    +(-
    0.67
    प्पा
    0.66
    ɹ
    0.65
    +$
    0.65
    -(
    0.64
    ^{+
    0.63
    weh
    0.62
    POSITIVE LOGITS
     Vietnam
    0.94
     Mekong
    0.93
     Saigon
    0.92
     Việt
    0.89
    Vietnam
    0.89
     Hanoi
    0.83
     Latvij
    0.80
     vietnam
    0.78
     ಸಂಸ್ಥ
    0.78
     Nokia
    0.76
    Act Density 0.079%

    No Known Activations