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

    Neuronpedia

    INDEX
    Explanations

    demonstrates growth or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     змі
    0.51
    InData
    0.49
    фель
    0.48
     مرك
    0.48
     Infrast
    0.47
     инфраструк
    0.46
     Segurança
    0.46
    ഷ്യ
    0.46
    чні
    0.45
    孛
    0.44
    POSITIVE LOGITS
    m
    0.51
    div
    0.51
     lup
    0.50
     revolve
    0.47
     eel
    0.47
     grandma
    0.46
     February
    0.46
     weave
    0.45
    vä
    0.44
    illa
    0.44
    Act Density 0.000%

    No Known Activations