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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or scientific relationships and concepts

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

    Follows articles (a, in, the) or prepositions

    np_acts-logits-general · gemini-2.0-flash

    conversely or on the other hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.68
     particulière
    -0.65
    -0.64
     يتيمه
    -0.64
    AsUp
    -0.64
    Jîn
    -0.63
     erwähnten
    -0.59
    </blockquote>
    -0.58
    >*/
    -0.58
    </h3>
    -0.58
    POSITIVE LOGITS
     sebaliknya
    0.81
     наоборот
    0.78
     altrett
    0.69
     conversely
    0.68
     Conversely
    0.66
     dagegen
    0.65
    逆に
    0.64
     Sedangkan
    0.63
    另一
    0.63
    Conversely
    0.63
    Act Density 1.825%

    No Known Activations