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

    Neuronpedia

    INDEX
    Explanations

    harry potter and related content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Date
    0.63
    Sph
    0.63
    Material
    0.61
    Add
    0.60
    of
    0.60
    Sp
    0.59
    Nav
    0.57
    Editor
    0.57
    Hide
    0.57
    End
    0.56
    POSITIVE LOGITS
    ០០
    0.62
     Programmes
    0.60
    ོང་
    0.59
     cun
    0.58
    ؤ
    0.58
     prowad
    0.57
     proteína
    0.57
    т
    0.57
    м
    0.57
     Tribun
    0.56
    Act Density 0.001%

    No Known Activations