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

    Neuronpedia

    INDEX
    Explanations

    lien

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denomin
    -0.07
     Organizations
    -0.07
     ngu
    -0.07
     попада
    -0.06
    .peek
    -0.06
     oro
    -0.06
    “And
    -0.06
    olvable
    -0.06
    rellas
    -0.06
    clarations
    -0.06
    POSITIVE LOGITS
     lien
    0.13
    WER
    0.06
    /print
    0.06
    您
    0.06
    _GEN
    0.06
     relies
    0.06
     hyperlink
    0.06
    ере
    0.06
     суб
    0.06
    <ID
    0.06
    Act Density 0.001%

    No Known Activations