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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swiftly
    -0.07
     trong
    -0.07
    ımda
    -0.07
    iid
    -0.06
    _FT
    -0.06
    (fr
    -0.06
     quadratic
    -0.06
    ordes
    -0.06
     Hermes
    -0.06
     Handles
    -0.06
    POSITIVE LOGITS
     ENTRY
    0.06
    ]↵
    0.06
     europé
    0.06
    ี้↵
    0.06
    OURNAL
    0.06
    pagen
    0.06
    }")↵
    0.06
     lol
    0.06
     muslim
    0.06
    igits
    0.06
    Act Density 0.016%

    No Known Activations