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

    Neuronpedia

    INDEX
    Explanations

    ized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weniger
    -0.06
     compensated
    -0.06
     _|
    -0.06
     بار
    -0.06
    วร
    -0.06
    grounds
    -0.06
     LAT
    -0.06
    ابی
    -0.06
     grass
    -0.06
     Editors
    -0.06
    POSITIVE LOGITS
    ----------------------------------------------------------------------
    0.07
     accom
    0.06
    ระยะ
    0.06
     ging
    0.06
     Josh
    0.06
    Josh
    0.06
     Goal
    0.06
    ValueGenerationStrategy
    0.06
    塚
    0.06
     Joshua
    0.06
    Act Density 0.023%

    No Known Activations