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

    Neuronpedia

    INDEX
    Explanations

    roblox lua scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çıkarm
    0.88
     filenames
    0.82
    云计算
    0.75
    Production
    0.72
     çıkar
    0.71
     vécu
    0.70
    PIP
    0.70
    ኀ
    0.70
    Emails
    0.69
     주민
    0.69
    POSITIVE LOGITS
    waste
    0.64
    eding
    0.62
    mutate
    0.60
    organisation
    0.60
    reward
    0.60
    ponder
    0.59
    Tn
    0.59
    enden
    0.59
    lant
    0.59
     Tn
    0.58
    Act Density 0.002%

    No Known Activations