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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .White
    -0.07
    Beta
    -0.07
    _STARTED
    -0.07
     人
    -0.06
    県
    -0.06
    orph
    -0.06
    	hit
    -0.06
     と
    -0.06
    (year
    -0.06
     through
    -0.06
    POSITIVE LOGITS
    m
    0.09
    (m
    0.07
     the
    0.07
     vstup
    0.07
    	m
    0.07
     m
    0.07
     son
    0.07
     proces
    0.07
    -m
    0.07
     a
    0.07
    Act Density 0.008%

    No Known Activations