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

    Neuronpedia

    INDEX
    Explanations

    professions ending in "or"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _category
    -0.07
     Example
    -0.07
     thé
    -0.07
    output
    -0.07
     ou
    -0.07
     ster
    -0.07
    ::_('
    -0.07
     '('
    -0.07
     enc
    -0.07
    (request
    -0.07
    POSITIVE LOGITS
    aal
    0.06
    otland
    0.06
    İS
    0.05
    uiten
    0.05
     Pods
    0.05
     AssetImage
    0.05
     Ames
    0.05
    わ
    0.05
    loid
    0.05
     lắng
    0.05
    Act Density 0.050%

    No Known Activations