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

    Neuronpedia

    INDEX
    Explanations

    commands or requests for action

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

    just verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gants
    -0.51
     sklep
    -0.49
    leski
    -0.48
     zimowa
    -0.48
     weihnachten
    -0.47
     kurtka
    -0.46
     kopling
    -0.46
     aikana
    -0.46
     więcej
    -0.46
     jopa
    -0.45
    POSITIVE LOGITS
    simply
    0.69
    just
    0.62
     Просто
    0.61
     simply
    0.60
    Simply
    0.59
     Simplemente
    0.59
     simplemente
    0.59
    ftagPool
    0.58
     Simply
    0.57
    Einfach
    0.57
    Act Density 0.084%

    No Known Activations