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

    Neuronpedia

    INDEX
    Explanations

    electrolyte imbalances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ется
    0.59
     I
    0.59
    ように
    0.59
    ikult
    0.56
     cliché
    0.54
    ie
    0.52
    вени
    0.52
     mindless
    0.52
    ="#!"
    0.52
     layman
    0.52
    POSITIVE LOGITS
     of
    0.70
    αρ
    0.67
     aquare
    0.67
    O
    0.66
    0
    0.63
     étaient
    0.62
    د
    0.62
     by
    0.60
    با
    0.60
     frutas
    0.60
    Act Density 0.001%

    No Known Activations