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

    Neuronpedia

    INDEX
    Explanations

    Text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [n
    -0.07
     tang
    -0.07
     numerical
    -0.07
     critic
    -0.07
    .ncbi
    -0.06
    orarily
    -0.06
    .list
    -0.06
    		  ↵
    -0.06
     exploring
    -0.06
    Sample
    -0.06
    POSITIVE LOGITS
    /cs
    0.08
    ry
    0.06
     Yıl
    0.06
    'M
    0.06
    -unstyled
    0.06
    .spotify
    0.06
     міс
    0.06
     expended
    0.06
    ."},↵
    0.06
     женщина
    0.06
    Act Density 0.301%

    No Known Activations