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

    Neuronpedia

    INDEX
    Explanations

    Neuralink

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    1.63
    ו
    1.43
    The
    1.34
    nya
    1.30
    as
    1.25
    ina
    1.24
    م
    1.24
    il
    1.23
    est
    1.22
     are
    1.22
    POSITIVE LOGITS
    ل
    1.40
    미
    1.40
    𝒈
    1.37
    دارة
    1.30
    バ
    1.30
     Hesap
    1.26
    岄
    1.26
    ᱗
    1.25
    }=
    1.23
    ږئ
    1.23
    Act Density 0.000%

    No Known Activations