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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations in texts

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

    via followed by source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     objectifs
    -0.40
     arbres
    -0.33
    secuencias
    -0.33
     ennemis
    -0.33
     plantel
    -0.32
     tyre
    -0.32
     ayuntamiento
    -0.32
     dramatique
    -0.31
     réal
    -0.31
     éste
    -0.31
    POSITIVE LOGITS
     via
    1.48
    Via
    1.46
     Via
    1.35
    via
    1.35
     VIA
    1.22
    VIA
    1.17
     vía
    1.04
    vía
    0.94
    Vía
    0.93
     Vía
    0.89
    Act Density 0.005%

    No Known Activations