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

    Neuronpedia

    INDEX
    Explanations

    procedural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सहायता
    -0.08
    大胆
    -0.08
    reasonable
    -0.08
    Imagine
    -0.08
     únicamente
    -0.07
     aðeins
    -0.07
     용
    -0.07
     कल्प
    -0.07
     assegurar
    -0.07
    ieß
    -0.07
    POSITIVE LOGITS
     Transcript
    0.08
     transcript
    0.08
    _env
    0.08
    _eps
    0.07
    ixture
    0.07
     Economics
    0.07
     fenn
    0.07
     Fore
    0.07
     took
    0.07
     transcripts
    0.07
    Act Density 0.000%

    No Known Activations