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

    Neuronpedia

    INDEX
    Explanations

    Facebook buttons and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     полез
    0.47
     индек
    0.47
     фильмы
    0.44
     чуде
    0.43
     лучше
    0.43
     немного
    0.42
     сильнее
    0.42
     более
    0.41
     Skyscrapers
    0.41
     этой
    0.41
    POSITIVE LOGITS
     impartiality
    0.42
     prerogative
    0.42
    incorrect
    0.40
     presumptive
    0.39
     registrar
    0.37
     severity
    0.37
     referee
    0.37
     registr
    0.37
    ग्गा
    0.37
     registrer
    0.36
    Act Density 0.000%

    No Known Activations