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

    Neuronpedia

    INDEX
    Explanations

    survive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pictures
    -0.29
    (pm
    -0.28
    è¿ĩå¾Ģ
    -0.27
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.27
    oli
    -0.26
    å¾Ģäºĭ
    -0.25
    ISTICS
    -0.25
    .picture
    -0.24
     Howe
    -0.24
    awa
    -0.24
    POSITIVE LOGITS
    欢è¿İ
    0.28
    dex
    0.25
     bevor
    0.25
    æĿ¥çĶµ
    0.24
    çĥ¦
    0.24
     Optional
    0.23
    æµģåĬ¨
    0.23
    isbn
    0.23
    Optional
    0.23
    æµģéĩı
    0.23
    Act Density 0.135%

    No Known Activations