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

    Neuronpedia

    INDEX
    Explanations

    comparisons between data or statistics

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

    comparing two things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.65
     للمعارف
    -0.53
     autorytatywna
    -0.53
     ***!
    -0.53
    arangay
    -0.49
     Sándor
    -0.49
     Schwer
    -0.48
    Читати
    -0.48
     tartalomajánló
    -0.48
    AddTagHelper
    -0.48
    POSITIVE LOGITS
     SwitchCompat
    0.37
     compare
    0.35
     rispetto
    0.35
     comparison
    0.34
     compared
    0.34
     comparaison
    0.33
     inverse
    0.32
     jäm
    0.31
     versus
    0.31
     kohdetta
    0.31
    Act Density 0.034%

    No Known Activations