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

    Neuronpedia

    INDEX
    Explanations

    themes related to toxicity and biological processes

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

    ending in "tic", "tes", "tion", "te", or "ted"

    np_acts-logits-general · gemini-2.0-flash

    multiple, multiplet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    -0.64
     дописавши
    -0.63
    TintMode
    -0.62
    MessageTagHelper
    -0.60
    ING
    -0.59
     AssemblyCompany
    -0.59
    UnknownFieldSet
    -0.59
    AutoScaleMode
    -0.58
     jScrollPane
    -0.58
    SBATCH
    -0.57
    POSITIVE LOGITS
    te
    1.00
    ted
    0.94
    ties
    0.93
    ts
    0.89
    tic
    0.82
    tes
    0.78
    tie
    0.78
    ty
    0.74
    table
    0.68
    ti
    0.68
    Act Density 0.453%

    No Known Activations