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

    Neuronpedia

    INDEX
    Explanations

    convert units or data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗁
    0.44
    thisTrack
    0.40
    >\
    0.38
    notlocked
    0.38
    𝖺
    0.38
    燬
    0.37
    ufieurs
    0.36
    茆
    0.36
     messageFields
    0.35
    सेशन
    0.35
    POSITIVE LOGITS
     Bur
    0.39
     Fair
    0.38
     Dur
    0.38
     verbal
    0.37
    0.37
     Percent
    0.37
     rider
    0.37
     remove
    0.35
     TEXT
    0.35
    -
    0.34
    Act Density 0.000%

    No Known Activations