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

    Neuronpedia

    INDEX
    Explanations

    code structure keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dropdown
    0.38
    풀
    0.38
    dropdown
    0.37
     frivolous
    0.37
    logrus
    0.36
    NewLine
    0.36
    AssetsRequest
    0.35
    healing
    0.35
    훌
    0.35
     আগ
    0.34
    POSITIVE LOGITS
    orar
    0.45
     knows
    0.43
     Knows
    0.42
    ARIO
    0.41
    ARIOS
    0.39
     viss
    0.38
    arios
    0.37
     vivos
    0.37
     vécu
    0.36
     médicos
    0.36
    Act Density 0.164%

    No Known Activations