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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    以ä¸ĭç®Ģ称
    -0.28
    çªģåĩºéĹ®é¢ĺ
    -0.27
    entifier
    -0.25
     Fault
    -0.24
    (by
    -0.24
    ault
    -0.24
     fault
    -0.24
     Adapt
    -0.23
    æĤª
    -0.23
    UILTIN
    -0.23
    POSITIVE LOGITS
    佬
    0.34
    个交æĺĵ
    0.27
    izona
    0.26
    kees
    0.26
    ynes
    0.25
    ammed
    0.25
    æµ·çĽĹ
    0.25
    éĻįä»·
    0.25
    ired
    0.25
    ibase
    0.25
    Act Density 0.009%

    No Known Activations