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

    Neuronpedia

    INDEX
    Explanations

    positive attributes and suitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mainly
    1.00
     hauptsächlich
    0.96
    𓏧
    0.90
    اویر
    0.88
     głównie
    0.88
    Mostly
    0.86
    primarily
    0.85
    または
    0.84
    DueDate
    0.83
    Due
    0.83
    POSITIVE LOGITS
     potential
    1.08
     allowing
    1.01
     considerations
    0.98
     ability
    0.93
     потенциа
    0.93
     wanting
    0.91
     imagining
    0.90
     when
    0.90
     enabling
    0.89
     contemplating
    0.88
    Act Density 0.050%

    No Known Activations