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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Predicate
    -0.07
    precation
    -0.07
    ύ
    -0.06
    .Phone
    -0.06
    または
    -0.06
     retina
    -0.06
     dwarf
    -0.06
     Maid
    -0.06
    这是
    -0.06
     kaydet
    -0.06
    POSITIVE LOGITS
     audio
    0.07
     became
    0.06
     clad
    0.06
     become
    0.06
     ResourceManager
    0.06
     Rid
    0.06
     lies
    0.06
    clair
    0.06
    ULL
    0.06
    swers
    0.06
    Act Density 0.037%

    No Known Activations