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

    Neuronpedia

    INDEX
    Explanations

    past time loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CollectedField
    0.48
    施設の
    0.43
    紺
    0.43
     desk
    0.40
    pronged
    0.40
    RationalValue
    0.40
    いただいた
    0.39
    PanelVisual
    0.39
    などが
    0.39
    提出的
    0.38
    POSITIVE LOGITS
     atividade
    0.47
    df
    0.45
    আমাদের
    0.43
     adata
    0.43
    بعد
    0.42
     distância
    0.41
     Screenshots
    0.41
     dns
    0.41
    R
    0.40
     Primeira
    0.40
    Act Density 0.001%

    No Known Activations