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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rf
    -0.07
    .Of
    -0.06
    HLT
    -0.06
    MARK
    -0.06
    Wat
    -0.06
    acts
    -0.06
     sistema
    -0.06
    92
    -0.06
     boiler
    -0.06
    LC
    -0.06
    POSITIVE LOGITS
    öt
    0.07
    	CG
    0.06
    handle
    0.06
    SnackBar
    0.06
    强
    0.06
     nive
    0.06
     mimeType
    0.06
    IGNORE
    0.06
    .gb
    0.06
     внес
    0.06
    Act Density 0.210%

    No Known Activations