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

    Neuronpedia

    INDEX
    Explanations

    Chrome/version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bőr
    0.37
     Windows
    0.37
     ധാ
    0.37
    ᖇ
    0.37
    שׁ
    0.36
    ითხ
    0.36
     irradiated
    0.36
     სისტ
    0.36
     viscoelastic
    0.35
    olactone
    0.35
    POSITIVE LOGITS
    bandSize
    0.48
    9
    0.40
    enció
    0.40
    eland
    0.36
    squarePos
    0.36
     پسند
    0.34
    控え
    0.34
    5
    0.34
    悍
    0.34
     Sayles
    0.34
    Act Density 0.001%

    No Known Activations