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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion or belief about key details

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

    to be fair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OFDb
    -0.44
     otomatig
    -0.44
     Италијани
    -0.40
    #
    -0.38
    PerformLayout
    -0.38
     RISERV
    -0.37
    SBATCH
    -0.36
     actifs
    -0.35
     мәкал
    -0.35
     käytet
    -0.35
    POSITIVE LOGITS
    gebob
    0.59
     Avo
    0.55
    justed
    0.52
    Addo
    0.52
    ABUL
    0.52
     misunder
    0.51
    arote
    0.51
     Anson
    0.50
    uvwxyz
    0.49
     Alo
    0.49
    Act Density 0.071%

    No Known Activations