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

    Neuronpedia

    INDEX
    Explanations

    references to animals and comparisons involving metaphors

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

    idiomatic expressions and metaphors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*++
    -0.35
    ForType
    -0.31
     $:
    -0.30
    stdlib
    -0.29
    ftant
    -0.28
    AUR
    -0.28
    lyn
    -0.28
    sprint
    -0.28
     propa
    -0.28
    sv
    -0.28
    POSITIVE LOGITS
     astore
    0.68
    StoryboardSegue
    0.66
     MainAxisSize
    0.62
     NSCoder
    0.61
     betweenstory
    0.61
     ChromeDriver
    0.58
     ModelRenderer
    0.57
     newOwner
    0.57
    AndEndTag
    0.57
    ſehen
    0.56
    Act Density 0.079%

    No Known Activations