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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     officia
    -0.08
    ьев
    -0.08
    );?>↵
    -0.08
    ｡
    -0.08
    іністра
    -0.08
    eluaran
    -0.07
     STILL
    -0.07
     ഔ
    -0.07
     demonstrated
    -0.07
    كمال
    -0.07
    POSITIVE LOGITS
    fried
    0.08
     Fried
    0.08
     Gerät
    0.07
     supernatural
    0.07
    (Device
    0.07
    Probe
    0.07
     recon
    0.07
    (Map
    0.07
    woods
    0.07
    coming
    0.07
    Act Density 0.000%

    No Known Activations