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

    Neuronpedia

    INDEX
    Explanations

    order and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outpatient
    0.53
     epidemiological
    0.48
     psychiatry
    0.48
     epidemi
    0.46
     Pediatric
    0.46
    ент
    0.45
     paleont
    0.45
     pediat
    0.45
     pediatric
    0.44
     isolating
    0.44
    POSITIVE LOGITS
    설
    0.46
    ácie
    0.44
    cijas
    0.43
    vorschau
    0.43
    că
    0.42
    Ри
    0.42
    மண
    0.42
     അരി
    0.42
    as
    0.42
    üse
    0.42
    Act Density 0.000%

    No Known Activations