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

    Neuronpedia

    INDEX
    Explanations

    Narrative text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	spec
    -0.07
    LTRB
    -0.07
     RectTransform
    -0.07
    初期
    -0.07
    獗
    -0.07
     Content
    -0.07
     perms
    -0.07
    -read
    -0.07
    _Speed
    -0.07
    .success
    -0.07
    POSITIVE LOGITS
    Option
    0.06
    ]+)/
    0.06
    회사
    0.06
     OMIT
    0.06
     tower
    0.06
    Danger
    0.06
     tav
    0.06
     sang
    0.06
    ulatory
    0.06
    负担
    0.06
    Act Density 0.146%

    No Known Activations