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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or entities

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

    names like Rodrigo, Rowling, DuPont

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dimensões
    -0.51
    protoimpl
    -0.51
    áctenos
    -0.49
    Grüße
    -0.48
     russes
    -0.48
    carteles
    -0.45
    chränk
    -0.45
    ειτουργ
    -0.45
    Tikang
    -0.45
    convite
    -0.45
    POSITIVE LOGITS
     Rodrigo
    1.54
    Rodrigo
    1.33
     rodrigo
    0.89
    ::_('
    0.69
    himovic
    0.68
    lc
    0.57
     Enix
    0.49
    InputBorder
    0.48
    GTCX
    0.46
    Vanjske
    0.45
    Act Density 0.002%

    No Known Activations