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

    Neuronpedia

    INDEX
    Explanations

    ERS IRS PRS CRS ARS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bs
    0.40
    েশন
    0.40
    áb
    0.38
    cks
    0.38
     كر
    0.38
    ﺌ
    0.37
    rier
    0.37
    жко
    0.37
    েকে
    0.37
    bler
    0.36
    POSITIVE LOGITS
    heed
    0.44
    Yours
    0.43
     poursu
    0.39
    pective
    0.39
     thriving
    0.39
    Touchable
    0.38
    संस्करण
    0.38
    Unified
    0.38
    ాను
    0.38
     yours
    0.37
    Act Density 0.007%

    No Known Activations