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

    Neuronpedia

    INDEX
    Explanations

    `using`, `conversion`, `conflict`, `publish`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turut
    0.43
     ikut
    0.42
    BIUM
    0.41
    ongono
    0.40
     skillet
    0.40
    ’
    0.40
     masque
    0.39
    ázej
    0.39
    '
    0.39
    arl
    0.39
    POSITIVE LOGITS
    ｔ
    0.43
    ᠶ
    0.42
    𝒞
    0.40
     exiled
    0.40
    來說
    0.39
    Ling
    0.39
    ുവരി
    0.38
    🦊
    0.38
    Pes
    0.38
     interpreting
    0.37
    Act Density 0.119%

    No Known Activations