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

    Neuronpedia

    INDEX
    Explanations

    you can change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknowns
    0.46
    糹
    0.42
    ándo
    0.42
     miscellaneous
    0.42
     дополнительных
    0.42
     daarbij
    0.42
     beklen
    0.41
    ﾈ
    0.41
     выпущен
    0.40
     samping
    0.40
    POSITIVE LOGITS
    改为
    0.65
    Change
    0.63
    改成
    0.63
     alternatively
    0.61
     change
    0.61
     cambiar
    0.59
     변경
    0.58
    change
    0.58
    Could
    0.58
     değiştir
    0.58
    Act Density 0.004%

    No Known Activations