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

    Neuronpedia

    INDEX
    Explanations

    jibber jabber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    1.55
    ções
    1.34
    ef
    1.27
    ena
    1.26
    ؤ
    1.25
    ume
    1.24
    우리
    1.24
    av
    1.23
    esh
    1.19
    ્યાર
    1.19
    POSITIVE LOGITS
    ع
    2.24
    ことができます
    1.59
    ことができる
    1.59
    ী
    1.59
    lük
    1.52
    te
    1.47
     confound
    1.46
     reiterate
    1.44
    誉
    1.42
    ні
    1.41
    Act Density 0.000%

    No Known Activations