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

    Neuronpedia

    INDEX
    Explanations

    visualization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shapes
    -0.07
    (seg
    -0.07
    �
    -0.06
     sotto
    -0.06
     ł
    -0.06
     Пра
    -0.06
    кра
    -0.06
    층
    -0.06
     thơm
    -0.06
    _documento
    -0.06
    POSITIVE LOGITS
    visor
    0.07
     visualization
    0.07
     fearless
    0.07
     감
    0.06
     visualize
    0.06
     happening
    0.06
    ave
    0.06
    Visual
    0.06
     foreseeable
    0.06
    %M
    0.06
    Act Density 0.007%

    No Known Activations