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

    Neuronpedia

    INDEX
    Explanations

    terms indicating potential candidates or selection processes

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

    candidate for further study or application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.35
     Monthly
    -0.35
     how
    -0.34
    AxisAlignment
    -0.34
    engesch
    -0.33
    serv
    -0.33
     Bul
    -0.32
    gods
    -0.31
    AndroidJUnit
    -0.30
     Electricity
    -0.30
    POSITIVE LOGITS
     candidate
    1.78
    Candidate
    1.75
     Candidate
    1.72
    candidate
    1.68
     CANDIDATE
    1.50
     Candidates
    1.45
     candidates
    1.43
    Candidates
    1.40
    candidates
    1.27
     candidato
    1.20
    Act Density 0.017%

    No Known Activations