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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amen
    -0.07
    2
    -0.06
    AppName
    -0.06
    cannot
    -0.06
    _REPLACE
    -0.06
    3
    -0.06
     cannot
    -0.06
    565
    -0.06
    _swap
    -0.06
    _ACTION
    -0.06
    POSITIVE LOGITS
     Views
    0.07
     sliders
    0.07
     THE
    0.07
    分钟
    0.07
    ै।↵
    0.07
     breath
    0.06
    iyor
    0.06
     밀
    0.06
    τια
    0.06
     toaster
    0.06
    Act Density 0.055%

    No Known Activations