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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raptors
    -0.07
    ogh
    -0.06
    -0.06
     ilgi
    -0.06
     Disorder
    -0.06
     Flu
    -0.06
     salon
    -0.06
    ⠀
    -0.05
    		↵	↵
    -0.05
    โรค
    -0.05
    POSITIVE LOGITS
     viv
    0.07
     Gross
    0.07
    .bo
    0.06
     disabling
    0.06
    classed
    0.06
     Ủy
    0.06
    (x
    0.06
     rect
    0.06
     développement
    0.06
     Threat
    0.06
    Act Density 0.016%

    No Known Activations