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

    Neuronpedia

    INDEX
    Explanations

    amsfonts and functional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ěr
    0.39
    ᓗ
    0.36
    margins
    0.36
     Фургала
    0.36
     밝
    0.35
    scoring
    0.35
    Ꭻ
    0.35
    p
    0.35
    ̥
    0.35
    跖
    0.34
    POSITIVE LOGITS
     curved
    0.45
     invitados
    0.43
     undeniable
    0.40
    autre
    0.40
     ouv
    0.40
    reihe
    0.40
     immaterial
    0.39
     soddisf
    0.39
     proveedores
    0.38
     satisfied
    0.38
    Act Density 0.000%

    No Known Activations