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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UBLISH
    -0.07
    Replacing
    -0.07
     bodies
    -0.07
     cauliflower
    -0.07
     body
    -0.07
    	Array
    -0.06
    -CS
    -0.06
     almak
    -0.06
     guise
    -0.06
     Kingston
    -0.06
    POSITIVE LOGITS
    dispatch
    0.06
     stip
    0.06
    SPATH
    0.06
    izzer
    0.06
     feminist
    0.06
    _kill
    0.06
    Permanent
    0.06
     interruptions
    0.06
    cludes
    0.06
     supernatural
    0.06
    Act Density 0.027%

    No Known Activations