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

    Neuronpedia

    INDEX
    Explanations

    MUI v5 components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Settings
    0.55
     Viking
    0.54
     Gild
    0.52
     Dinas
    0.51
     Kraków
    0.51
     Gda
    0.50
     Settings
    0.50
    莜
    0.48
     Saras
    0.47
     Mods
    0.47
    POSITIVE LOGITS
    plaat
    0.50
    Ｍ
    0.47
    ｙ
    0.46
    itrile
    0.45
     tử
    0.45
    Ｙ
    0.45
    ون
    0.45
    髄
    0.44
    теле
    0.44
     playfully
    0.44
    Act Density 0.000%

    No Known Activations