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
     copper
    -0.07
    oming
    -0.07
     gaming
    -0.06
    inated
    -0.06
    TypeDef
    -0.06
     smokers
    -0.06
    peg
    -0.06
     chin
    -0.06
    foo
    -0.06
     Dirty
    -0.06
    POSITIVE LOGITS
    .params
    0.06
     과
    0.06
     menstrual
    0.06
     cresc
    0.06
    .preferences
    0.06
     caret
    0.06
    .short
    0.06
    atisf
    0.06
    pause
    0.06
    	param
    0.06
    Act Density 0.012%

    No Known Activations