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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('?
    -0.06
    616
    -0.06
    .overflow
    -0.06
    φορά
    -0.06
     نور
    -0.06
    těl
    -0.06
     Yao
    -0.06
     Potential
    -0.05
    _PRICE
    -0.05
     -------------------------------------------------------------------------
    -0.05
    POSITIVE LOGITS
     alleges
    0.07
     halls
    0.07
    子
    0.07
    pdb
    0.07
     SqlCommand
    0.06
    riminal
    0.06
    ordinal
    0.06
    .IsActive
    0.06
     trp
    0.06
     lda
    0.06
    Act Density 0.015%

    No Known Activations