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

    Neuronpedia

    INDEX
    Explanations

    Slipping through the cracks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .symmetric
    -0.08
     realistic
    -0.08
     skilled
    -0.08
    .combine
    -0.08
     peat
    -0.08
    .hex
    -0.08
    .wso
    -0.08
    景
    -0.08
    .w
    -0.08
     justified
    -0.07
    POSITIVE LOGITS
    遗漏
    0.12
     deadlines
    0.11
     overlooked
    0.11
     ચૂ
    0.11
     oversight
    0.10
     missed
    0.10
     manquer
    0.10
     забы
    0.10
     olvid
    0.10
     своев
    0.10
    Act Density 0.056%

    No Known Activations