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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scale
    -0.07
    GUILayout
    -0.06
    icense
    -0.06
     ammonia
    -0.06
     EditorGUILayout
    -0.06
     MIS
    -0.06
    ِ
    -0.06
     CROSS
    -0.06
    Cmd
    -0.06
    acles
    -0.06
    POSITIVE LOGITS
     blinds
    0.08
     genesis
    0.07
     جریان
    0.07
    robat
    0.07
     cây
    0.06
    apper
    0.06
     kesin
    0.06
    .ActionBar
    0.06
    ніш
    0.06
     genç
    0.06
    Act Density 0.001%

    No Known Activations