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

    Neuronpedia

    INDEX
    Explanations

    heard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĦı
    -0.28
    ej
    -0.25
    飧æĢ§
    -0.24
    rais
    -0.24
     Äijại
    -0.24
     younger
    -0.24
    ONO
    -0.24
    à¹Ģà¸ī
    -0.23
    çŁ³æĿIJ
    -0.23
     older
    -0.23
    POSITIVE LOGITS
    thesis
    0.32
    &action
    0.27
    theses
    0.26
    ä¸įéĢļ
    0.26
     anthrop
    0.26
    èħ¥
    0.26
    lemn
    0.25
     Inbox
    0.25
    edin
    0.24
    bane
    0.24
    Act Density 0.141%

    No Known Activations