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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions and context indicators

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

    introducing context or modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     todella
    -0.41
     geval
    -0.40
    GTCX
    -0.38
     muhte
    -0.36
     gehouden
    -0.35
    ůr
    -0.35
     bepaalde
    -0.35
     gerçekten
    -0.35
     siis
    -0.34
     yani
    -0.34
    POSITIVE LOGITS
    AndEndTag
    0.77
    tonode
    0.63
    rylic
    0.53
    ########.
    0.52
     كومونز
    0.51
     насељу
    0.49
     verſ
    0.48
    delwed
    0.48
    ſcher
    0.47
     hobbies
    0.46
    Act Density 0.038%

    No Known Activations