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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /error
    -0.07
    _MOVE
    -0.06
    MESS
    -0.06
     commencement
    -0.06
     Road
    -0.06
     vér
    -0.06
    .hwp
    -0.06
    Val
    -0.06
    ΕΚ
    -0.06
    ipeg
    -0.06
    POSITIVE LOGITS
    니스
    0.07
     temple
    0.07
     financially
    0.07
     lowest
    0.07
     Highest
    0.06
    bone
    0.06
    	my
    0.06
     optical
    0.06
    Restr
    0.06
     деле
    0.06
    Act Density 0.007%

    No Known Activations