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

    Neuronpedia

    INDEX
    Explanations

    common words followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exotic
    0.42
     phony
    0.41
    oldi
    0.40
     daqu
    0.39
     manner
    0.38
    judice
    0.38
     star
    0.36
    cath
    0.36
     temporarily
    0.36
     tij
    0.36
    POSITIVE LOGITS
    ্টের
    0.43
    𝐗
    0.42
     Henning
    0.40
     Careful
    0.40
     просмо
    0.39
     ಜೀವ
    0.37
    ാലി
    0.37
     الحي
    0.37
    ργαν
    0.37
    ൭
    0.37
    Act Density 0.000%

    No Known Activations