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

    Neuronpedia

    INDEX
    Explanations

    screen settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mát
    -0.06
     UTF
    -0.06
     onze
    -0.06
    �
    -0.06
    tiği
    -0.06
     اع
    -0.06
     comboBox
    -0.06
     يوم
    -0.05
     geben
    -0.05
     jot
    -0.05
    POSITIVE LOGITS
    rotate
    0.07
     reconstruct
    0.07
    ▲
    0.06
    HO
    0.06
    /gr
    0.06
    _Surface
    0.06
    ské
    0.06
     заст
    0.06
    原因
    0.06
     lands
    0.06
    Act Density 0.057%

    No Known Activations