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

    Neuronpedia

    INDEX
    Explanations

    ATE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     investigates
    -0.09
     investigar
    -0.08
     investigations
    -0.08
     independent
    -0.08
     investigation
    -0.08
     unabh
    -0.08
     {↵/
    -0.08
    wan
    -0.08
     investigating
    -0.08
     independente
    -0.07
    POSITIVE LOGITS
     rid
    0.08
     Rendering
    0.08
     Varianten
    0.08
     ಹರ
    0.07
    _RENDER
    0.07
     varia
    0.07
    _render
    0.07
     raffin
    0.07
     beacon
    0.07
     Navig
    0.07
    Act Density 0.000%

    No Known Activations