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

    Neuronpedia

    INDEX
    Explanations

    references to newness or additional items and concepts

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

    Follows "additional," "another," or "extra"

    np_acts-logits-general · gemini-2.0-flash

    additional or extra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.64
     còn
    -0.63
     restantes
    -0.62
     remaining
    -0.54
     rispet
    -0.53
     Exactos
    -0.52
    -0.50
     lastly
    -0.50
     renewed
    -0.49
     Lingkungan
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.73
     niż
    0.71
     برانيه
    0.66
    hermosa
    0.64
    AsUp
    0.63
     layer
    0.61
     round
    0.59
    artige
    0.59
     than
    0.58
    AnchorStyles
    0.58
    Act Density 0.293%

    No Known Activations