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

    Neuronpedia

    INDEX
    Explanations

    terms related to compatibility and associated issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    compatibility mode or issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Usted
    -0.47
     rédaction
    -0.47
     voici
    -0.45
     varones
    -0.45
    selben
    -0.43
    writerow
    -0.42
     usted
    -0.42
     erster
    -0.41
     Erster
    -0.41
     récit
    -0.40
    POSITIVE LOGITS
     compatibility
    2.36
     Compatibility
    2.22
    compatibility
    2.14
    Compatibility
    2.09
     incompatibility
    1.94
     compati
    1.88
     compat
    1.82
     incompati
    1.78
     COMPAT
    1.73
    compati
    1.71
    Act Density 0.009%

    No Known Activations