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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     shootings
    1.09
     atrocities
    1.04
    ació
    1.01
    沖縄
    1.00
    1.00
     bombings
    0.98
    íncipe
    0.97
     rebounds
    0.97
     ammo
    0.95
     stimuli
    0.95
    POSITIVE LOGITS
    o
    1.24
     объем
    1.17
    赳
    1.17
    ו
    1.15
    ه
    1.15
    ictionaries
    1.13
     hãy
    1.12
    вання
    1.11
    ה
    1.11
     łącz
    1.10
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.