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

    Neuronpedia

    INDEX
    Explanations

    common * . ): glob

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    由
    0.44
    ش
    0.44
    Cl
    0.43
    LE
    0.43
    र्ग
    0.43
    ੋ
    0.42
    Consult
    0.42
    Pizza
    0.42
    ُ
    0.41
    UM
    0.41
    POSITIVE LOGITS
     đẹp
    0.48
     dredging
    0.48
    aeskeygenassist
    0.47
     chuyện
    0.46
    yrıca
    0.45
    apadam
    0.45
    y
    0.45
     Olympian
    0.45
     Psal
    0.44
     مغربی
    0.44
    Act Density 0.002%

    No Known Activations