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

    Neuronpedia

    INDEX
    Explanations

    domain names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bas
    -0.06
     supporters
    -0.06
    	person
    -0.06
     음악
    -0.06
    	address
    -0.06
     zde
    -0.06
    力を
    -0.06
    ुक
    -0.06
    	current
    -0.06
     Cypress
    -0.06
    POSITIVE LOGITS
    .DOM
    0.07
     ghost
    0.07
    ได
    0.07
     خل
    0.07
     subset
    0.07
    .All
    0.07
    colo
    0.06
    nard
    0.06
    erte
    0.06
    Bio
    0.06
    Act Density 0.007%

    No Known Activations