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

    Neuronpedia

    INDEX
    Explanations

    Titles and genealogy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astes
    -0.06
    ropped
    -0.06
    pping
    -0.06
    doing
    -0.06
     giản
    -0.06
     علي
    -0.06
    imbabwe
    -0.06
    KH
    -0.06
     kelim
    -0.05
    _o
    -0.05
    POSITIVE LOGITS
    /start
    0.07
     TNT
    0.07
    Merge
    0.07
    odega
    0.07
    (resources
    0.07
     Broadcom
    0.06
    ặc
    0.06
    ':
↵
    0.06
     Alternative
    0.06
     layers
    0.06
    Act Density 0.038%

    No Known Activations