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

    Neuronpedia

    INDEX
    Explanations

    mentions of societal structures and established norms

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

    repetition, routine, monotony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balleur
    -0.60
     HasFactory
    -0.59
    ########.
    -0.54
    BagConstraints
    -0.52
     vPvB
    -0.52
     Normdatei
    -0.50
     ModelRenderer
    -0.50
     noDo
    -0.49
    IKit
    -0.49
    sic
    -0.49
    POSITIVE LOGITS
     rutina
    0.44
     routine
    0.40
    Попис
    0.39
     repetition
    0.37
    __*/
    0.36
     marié
    0.33
     Sénat
    0.33
     coupable
    0.32
     compromiso
    0.32
     monotony
    0.31
    Act Density 0.092%

    No Known Activations