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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AM
    -0.07
     JB
    -0.06
    ороз
    -0.06
    VIDIA
    -0.06
    .newArrayList
    -0.06
     {};↵↵
    -0.06
    TypeID
    -0.06
     Schumer
    -0.06
    _inter
    -0.06
    	want
    -0.06
    POSITIVE LOGITS
     Musk
    0.07
     Počet
    0.07
     clases
    0.07
     dest
    0.07
    register
    0.06
    (fixture
    0.06
     požadav
    0.06
    资金
    0.06
    шее
    0.06
     transformation
    0.06
    Act Density 0.010%

    No Known Activations