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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    暹
    -0.07
    .API
    -0.07
    erosis
    -0.07
     artificial
    -0.07
    𝕦
    -0.07
    🧪
    -0.07
    ayar
    -0.06
    alyzer
    -0.06
     ب
    -0.06
     froze
    -0.06
    POSITIVE LOGITS
    dr
    0.07
    较好的
    0.07
    可靠
    0.07
    rangle
    0.07
    รายงาน
    0.07
     Grim
    0.07
     lending
    0.07
    合适
    0.07
    饲养
    0.07
    .gener
    0.07
    Act Density 0.005%

    No Known Activations