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

    Neuronpedia

    INDEX
    Explanations

    Reducing or controlling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _IDX
    -0.08
    تم
    -0.07
     >
↵
    -0.07
    _arg
    -0.07
    Submitted
    -0.06
    _PO
    -0.06
    /spec
    -0.06
    办
    -0.06
    (param
    -0.06
    	Block
    -0.06
    POSITIVE LOGITS
    こちら
    0.07
     [][]
    0.07
     simmer
    0.07
     chill
    0.07
     pause
    0.07
     subdued
    0.07
    ób
    0.06
     ner
    0.06
     defenses
    0.06
     manic
    0.06
    Act Density 0.017%

    No Known Activations