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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to personal experiences or shared activities

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

    travel and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.48
     αὐτ
    -0.44
     évêque
    -0.43
     senhora
    -0.41
    føl
    -0.40
     laiko
    -0.40
     virke
    -0.40
    rawDesc
    -0.39
     måneder
    -0.38
     environnement
    -0.38
    POSITIVE LOGITS
    PhysRev
    0.53
    extAlignment
    0.52
     estekak
    0.52
    /******/
    0.51
    xFFFFFF
    0.47
     Flight
    0.44
    enumii
    0.44
     Chr
    0.44
     FTX
    0.43
     MiG
    0.42
    Act Density 0.009%

    No Known Activations