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

    Neuronpedia

    INDEX
    Explanations

    idi

    np_max-act · gemini-2.0-flash

    image metadata, specifically related to the identification and scaling of images.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Venture
    -0.06
    mue
    -0.06
     Ferr
    -0.06
    achs
    -0.06
    ↵			↵
    -0.06
     Wax
    -0.06
     bombs
    -0.06
    Fort
    -0.06
    usr
    -0.06
     ↵            ↵
    -0.06
    POSITIVE LOGITS
     odpověd
    0.07
    玩
    0.07
    ticks
    0.07
    ":"","
    0.07
     everyday
    0.07
     progn
    0.07
    あの
    0.06
    Ú
    0.06
     tôi
    0.06
     offending
    0.06
    Act Density 0.001%

    No Known Activations