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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.69
    enumi
    -0.69
    AddTagHelper
    -0.64
    enumii
    -0.53
    userdetails
    -0.48
    AttributeSet
    -0.47
     JpaRepository
    -0.45
    yakarta
    -0.45
    ěli
    -0.43
    _{[
    -0.43
    POSITIVE LOGITS
     has
    0.76
     like
    0.72
    ிறது
    0.71
     chooses
    0.71
     decides
    0.68
     faces
    0.65
     develops
    0.63
     is
    0.63
     defaults
    0.63
     opts
    0.63
    Act Density 0.001%

    No Known Activations