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

    Neuronpedia

    INDEX
    Explanations

    terms related to quality and effectiveness

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

    superlative quality or rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.60
    unicip
    -0.57
    raulic
    -0.54
     uVar
    -0.54
     queſto
    -0.53
     témoig
    -0.52
     Verſ
    -0.52
    Související
    -0.51
    Islam
    -0.51
    blatt
    -0.51
    POSITIVE LOGITS
     best
    1.21
    best
    1.20
     meilleures
    1.16
    Best
    1.14
     BEST
    1.12
    BEST
    1.08
     migliore
    1.08
     Best
    1.05
     mejor
    1.05
    Better
    1.02
    Act Density 0.008%

    No Known Activations