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

    Neuronpedia

    INDEX
    Explanations

    information control and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    into
    0.60
     into
    0.51
     l
    0.49
     INTO
    0.48
    rin
    0.47
     इनटू
    0.46
    si
    0.46
     Into
    0.46
     in
    0.45
     One
    0.44
    POSITIVE LOGITS
    럽
    0.49
    жидан
    0.43
    бора
    0.42
     випад
    0.42
     타
    0.41
     Проци
    0.41
    LocalStorage
    0.41
     알
    0.41
    ларга
    0.41
    FormControl
    0.40
    Act Density 0.008%

    No Known Activations