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

    Neuronpedia

    INDEX
    Explanations

    consistent API, look, quality, service, branding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ާމ
    0.48
    anyone
    0.43
     жены
    0.42
     previa
    0.42
    ®,
    0.41
     Wort
    0.40
     Richtung
    0.40
     Bolsa
    0.40
     مجلس
    0.39
     Anyone
    0.39
    POSITIVE LOGITS
    개
    0.39
     Ss
    0.39
     `
    0.38
     '
    0.37
    েনারেল
    0.36
    鷹
    0.35
    牘
    0.35
    ુ
    0.35
     gateway
    0.34
    ິນ
    0.34
    Act Density 0.008%

    No Known Activations