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

    Neuronpedia

    INDEX
    Explanations

    technical language related to scientific analysis and methods

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

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    -0.44
     Ket
    -0.40
     betweenstory
    -0.38
     []).
    -0.38
     Corpus
    -0.36
     Socket
    -0.36
    Ket
    -0.35
     Hole
    -0.35
     Slide
    -0.35
     acorn
    -0.35
    POSITIVE LOGITS
    WebVitals
    0.55
    TagMode
    0.54
    Ƚ
    0.52
    цездатний
    0.50
    Tikang
    0.49
    AndEndTag
    0.49
     accurately
    0.48
     estudia
    0.47
     indywidual
    0.47
     determine
    0.47
    Act Density 0.087%

    No Known Activations