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

    Neuronpedia

    INDEX
    Explanations

    portion of a circle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warriors
    0.44
     rjf
    0.43
     stents
    0.42
     fiche
    0.40
     Vikipedi
    0.39
     thoracique
    0.39
    同學們
    0.38
     vélo
    0.38
    кономски
    0.38
     motorcycle
    0.37
    POSITIVE LOGITS
    representation
    0.53
    announced
    0.51
    спублі
    0.51
    applicable
    0.48
    Represent
    0.46
    mittedly
    0.46
    represents
    0.45
    Representation
    0.45
    recognition
    0.44
    proclaimed
    0.44
    Act Density 0.009%

    No Known Activations