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

    Neuronpedia

    INDEX
    Explanations

    ** and + punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *",
    0.35
    aient
    0.33
    xi
    0.32
    നെ
    0.32
    ര്‍ന്ന
    0.32
     طے
    0.32
    tyn
    0.32
     sver
    0.31
    人用
    0.31
     بچ
    0.31
    POSITIVE LOGITS
    }
    0.37
    ។
    0.36
    .
    0.36
    ސް
    0.36
    ()
    0.35
     entspre
    0.35
    قيقة
    0.34
    ();
    0.34
    })
    0.34
     साथ
    0.34
    Act Density 0.302%

    No Known Activations