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

    Neuronpedia

    INDEX
    Explanations

    opposition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .present
    -0.07
     swinger
    -0.07
    	It
    -0.07
    �
    -0.06
     getChild
    -0.06
     MF
    -0.06
     CWE
    -0.06
     Европ
    -0.06
    Maximum
    -0.06
    akhir
    -0.06
    POSITIVE LOGITS
     pedig
    0.07
    ANC
    0.07
     ředitel
    0.06
    _exclude
    0.06
    test
    0.06
    Medical
    0.06
    >"↵
    0.06
     gasoline
    0.06
    决
    0.06
     jestli
    0.06
    Act Density 0.020%

    No Known Activations