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

    Neuronpedia

    INDEX
    Explanations

    names and specific cultural references

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

    people's names and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     XJ
    -0.73
    JET
    -0.73
     Jojo
    -0.72
    Jaw
    -0.71
     defaultstate
    -0.70
     Joc
    -0.69
    JJ
    -0.69
    Jet
    -0.68
     Jof
    -0.68
     Jot
    -0.68
    POSITIVE LOGITS
     rozwój
    0.52
    بوابة
    0.52
     finnas
    0.49
     zimowa
    0.47
    AuthProvider
    0.47
     remonter
    0.46
     vertrouwen
    0.46
     dependencia
    0.45
     Vitória
    0.45
     transparencia
    0.45
    Act Density 0.323%

    No Known Activations