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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tent
    -0.28
    uten
    -0.27
    .grp
    -0.26
    æİĪ课
    -0.25
    çļĦæľĢä½³
    -0.25
     hero
    -0.24
    æľĢä½³
    -0.24
    cq
    -0.23
    GRP
    -0.23
    utan
    -0.23
    POSITIVE LOGITS
    å¹´çĶ±
    0.31
     adjust
    0.26
    emaakt
    0.25
    adera
    0.25
    syn
    0.24
    çĭIJçĭ¸
    0.24
    li
    0.24
     adj
    0.24
    gli
    0.24
    èģĶ
    0.24
    Act Density 0.130%

    No Known Activations