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

    Neuronpedia

    INDEX
    Explanations

    Release notes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лаж
    -0.06
    _len
    -0.06
    جز
    -0.06
    وش
    -0.06
    _DIST
    -0.05
     Meta
    -0.05
     ．
    -0.05
    :h
    -0.05
    ροι
    -0.05
     України
    -0.05
    POSITIVE LOGITS
     přízn
    0.07
     Ridge
    0.07
    iddled
    0.07
    _Config
    0.06
    <vector
    0.06
     Protector
    0.06
    Availability
    0.06
    0.06
    -scripts
    0.06
     demok
    0.06
    Act Density 0.117%

    No Known Activations