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

    Neuronpedia

    INDEX
    Explanations

    medical notes, procedures, or documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pessimism
    0.39
     precipitate
    0.38
     tud
    0.37
     remit
    0.37
     smi
    0.37
     deton
    0.37
     mitigated
    0.37
    🙏🙏
    0.37
    ड़ा
    0.37
    ड़ों
    0.36
    POSITIVE LOGITS
     indifferent
    0.41
     गोल
    0.41
    Diana
    0.41
    Denmark
    0.39
    handler
    0.39
    Fresh
    0.39
    Gol
    0.39
    Plane
    0.38
    ization
    0.38
    payer
    0.38
    Act Density 0.039%

    No Known Activations