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

    Neuronpedia

    INDEX
    Explanations

    hope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åī¯ç§ĺ书éķ¿
    -0.28
    åħŃ个
    -0.27
    社ä¼ļåıijå±ķ
    -0.26
    åĽŀçŃĶ
    -0.26
    åĩºåİĤ
    -0.25
     kho
    -0.25
    uff
    -0.25
     ÑįкÑģ
    -0.24
    OFFSET
    -0.24
     Sheet
    -0.24
    POSITIVE LOGITS
    æĻ´
    0.31
    umbo
    0.28
    ooth
    0.25
    onte
    0.25
     Trav
    0.25
    溶
    0.25
    alyzed
    0.25
    adem
    0.24
    ;break
    0.24
    ODO
    0.24
    Act Density 0.073%

    No Known Activations