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

    Neuronpedia

    INDEX
    Explanations

    pronoun then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लाभ
    0.53
     veterin
    0.50
    ंसक
    0.46
    ymptoms
    0.46
     rumin
    0.46
     shortcoming
    0.46
    malign
    0.45
     murderous
    0.45
     streaming
    0.44
     malad
    0.44
    POSITIVE LOGITS
     Vä
    0.55
     Dalai
    0.48
    O
    0.47
    V
    0.47
     Ö
    0.47
     Rosetta
    0.46
     Algerian
    0.46
     Iceland
    0.44
     Diwali
    0.44
     Ull
    0.44
    Act Density 0.007%

    No Known Activations