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

    Neuronpedia

    INDEX
    Explanations

    predecessor, capabilities, resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mình
    0.50
    šn
    0.46
    İstanbul
    0.46
    ("|"+"
    0.45
    ști
    0.45
     subway
    0.43
    "\
    0.43
    atmos
    0.43
    Featuring
    0.43
     コート
    0.42
    POSITIVE LOGITS
     potenciales
    0.48
     dependencia
    0.45
     FOUND
    0.44
     inferiores
    0.43
     capacitación
    0.43
     Cut
    0.42
     haberse
    0.42
    外的
    0.42
    يكا
    0.41
     erfolgre
    0.41
    Act Density 0.021%

    No Known Activations