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

    Neuronpedia

    INDEX
    Explanations

    degree signs and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รส
    0.42
     photospheric
    0.39
    itió
    0.38
    жі
    0.38
    ृह
    0.37
     মিয়া
    0.37
    чете
    0.37
    жными
    0.36
    rierte
    0.36
    行った
    0.36
    POSITIVE LOGITS
     Fairy
    0.42
     Snowdon
    0.41
     SN
    0.40
    SLE
    0.39
    acker
    0.38
     Argu
    0.38
     sn
    0.37
    weed
    0.37
     aiding
    0.36
     author
    0.36
    Act Density 0.000%

    No Known Activations