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

    Neuronpedia

    INDEX
    Explanations

    end of parenthetical explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.69
     （
    0.64
    <0x80>
    0.63
     (
    0.61
    ر
    0.60
    ح
    0.57
    ר
    0.55
    ยนต์
    0.50
    AR
    0.49
    𝟬
    0.49
    POSITIVE LOGITS
    ة
    0.85
    u
    0.84
    의
    0.75
    の
    0.73
    на
    0.70
    ى
    0.70
    ın
    0.68
    та
    0.63
    ின்
    0.63
    的
    0.63
    Act Density 0.663%

    No Known Activations