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

    Neuronpedia

    INDEX
    Explanations

    damage observed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     กราบ
    0.43
     Characters
    0.39
    ᇂ
    0.39
     Nauchno
    0.39
     Recherches
    0.38
    艿
    0.38
     Maugin
    0.37
     ಪ್ರ
    0.37
     TRANSPORTURI
    0.37
     FUT
    0.37
    POSITIVE LOGITS
     explanation
    0.41
    checkmark
    0.39
    rollo
    0.39
     journe
    0.39
     attendant
    0.38
    explanation
    0.38
     polo
    0.38
     legitimate
    0.38
     coalition
    0.38
     constellation
    0.38
    Act Density 0.000%

    No Known Activations