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

    Neuronpedia

    INDEX
    Explanations

    identifying who or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Об
    0.25
     a
    0.25
    。
    0.24
    "。
    0.23
    Щ
    0.23
    ?
    0.23
    自从
    0.23
    }$.
    0.22
    ك
    0.22
     बीच
    0.22
    POSITIVE LOGITS
     who
    0.34
     ktorí
    0.34
    한테
    0.28
    에게
    0.28
     quien
    0.27
    who
    0.26
     الذين
    0.26
     quienes
    0.25
     practising
    0.25
     którzy
    0.25
    Act Density 0.164%

    No Known Activations