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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yt
    -0.07
    Pragma
    -0.06
    (encoded
    -0.06
     Transparent
    -0.06
     حتی
    -0.06
    reso
    -0.06
    itting
    -0.06
    مود
    -0.06
    andom
    -0.06
     renovated
    -0.06
    POSITIVE LOGITS
     Treasury
    0.07
     metavar
    0.07
     Ja
    0.06
    swagen
    0.06
    ATHER
    0.06
    {j
    0.06
    sburgh
    0.06
     diagrams
    0.06
    evaluate
    0.06
    Always
    0.06
    Act Density 0.005%

    No Known Activations