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

    Neuronpedia

    INDEX
    Explanations

    words related to adapting or modifying things

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tz
    -0.07
    orough
    -0.06
    599
    -0.06
     wit
    -0.06
    str
    -0.06
    Downloader
    -0.06
    679
    -0.06
     Manus
    -0.06
     maxim
    -0.06
     ing
    -0.06
    POSITIVE LOGITS
     adapted
    0.17
    adapt
    0.15
     Adapt
    0.15
     courtesy
    0.13
    taken
    0.13
    (Source
    0.12
     source
    0.12
     adaptation
    0.12
     taken
    0.12
     Source
    0.11
    Act Density 0.045%

    No Known Activations