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

    Neuronpedia

    INDEX
    Explanations

    AI, nuclear, leveraged trading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     photore
    0.49
    endedores
    0.48
    াতিক
    0.44
     вікісторінку
    0.42
    lamualaikum
    0.41
    providers
    0.41
    ModelAttribute
    0.40
    allerg
    0.40
    𝙲
    0.40
     Fiverr
    0.39
    POSITIVE LOGITS
    于
    0.38
     cho
    0.37
     move
    0.36
     share
    0.36
     formula
    0.36
     किये
    0.35
     lau
    0.35
     Châu
    0.35
     could
    0.34
     Mania
    0.34
    Act Density 0.001%

    No Known Activations