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

    Neuronpedia

    INDEX
    Explanations

    potential, ability, necessity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.60
     The
    0.58
    The
    0.56
    the
    0.54
     THE
    0.51
     what
    0.50
     your
    0.48
    your
    0.47
    THE
    0.46
     দ্য
    0.46
    POSITIVE LOGITS
     necessário
    0.59
     необходимых
    0.54
     necessárias
    0.54
     necesarias
    0.53
     ability
    0.53
     necessary
    0.52
     توان
    0.52
     requisite
    0.52
     необхід
    0.51
     potrebné
    0.50
    Act Density 0.044%

    No Known Activations