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

    Neuronpedia

    INDEX
    Explanations

    examples with list syntax or enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essentielle
    0.92
     comprend
    0.90
    चीनी
    0.87
    جی
    0.86
     सीओ
    0.85
    mad
    0.84
     supérieures
    0.83
    给出
    0.83
    рі
    0.82
    гі
    0.82
    POSITIVE LOGITS
    ATION
    1.11
    ON
    0.95
    ോഗ്യ
    0.91
    AD
    0.89
    ES
    0.88
     TreeSet
    0.88
    IamPermissions
    0.88
    RE
    0.86
    U
    0.85
     Than
    0.84
    Act Density 0.001%

    No Known Activations