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

    Neuronpedia

    INDEX
    Explanations

    investigate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -produ
    -0.07
     unless
    -0.07
     MU
    -0.07
    .Q
    -0.06
     питания
    -0.06
    Dims
    -0.06
     Над
    -0.06
    .tool
    -0.06
     ais
    -0.06
     organizer
    -0.06
    POSITIVE LOGITS
     estado
    0.06
    ักก
    0.06
     Photography
    0.06
    DECLARE
    0.06
    шие
    0.06
    wizard
    0.06
    %)↵↵
    0.06
    вид
    0.06
    gatsby
    0.06
     ди
    0.06
    Act Density 0.022%

    No Known Activations