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

    Neuronpedia

    INDEX
    Explanations

    asking for permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inės
    0.32
    hra
    0.31
     eyelids
    0.31
    对自己
    0.31
     felt
    0.31
    aiman
    0.30
    اع
    0.30
     turns
    0.30
    ческими
    0.30
    鉐
    0.30
    POSITIVE LOGITS
    Ask
    0.46
    Permission
    0.45
    permission
    0.43
     permission
    0.43
     ask
    0.43
    Asking
    0.42
     rhet
    0.40
    Someone
    0.40
    Rex
    0.40
     परवानगी
    0.39
    Act Density 0.019%

    No Known Activations