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

    Neuronpedia

    INDEX
    Explanations

    references to proximity and frequency in context to locations or events

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

    occasional, next, local

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.51
     varandra
    -0.49
    ckså
    -0.46
     meurt
    -0.44
     táctil
    -0.43
     förslag
    -0.43
     florales
    -0.42
     auroit
    -0.42
     beban
    -0.41
     vendar
    -0.41
    POSITIVE LOGITS
    ">—
    0.58
    extAlignment
    0.57
    ⤹
    0.57
     classic
    0.57
     hot
    0.57
    ódó
    0.56
    ::-
    0.54
     best
    0.54
     ideal
    0.54
    +#+#
    0.54
    Act Density 0.016%

    No Known Activations