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

    Neuronpedia

    INDEX
    Explanations

    performing operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     segítség
    0.71
     самостоятельно
    0.67
     adquisición
    0.64
     correttamente
    0.64
     conformément
    0.63
     ausgewählt
    0.62
     Sélection
    0.61
     elucidation
    0.61
     prevails
    0.59
     meydana
    0.59
    POSITIVE LOGITS
     incorporate
    1.21
     include
    1.21
     vary
    1.18
     add
    1.13
     create
    1.10
     Include
    1.04
     integrate
    1.00
    Include
    0.98
     divide
    0.97
    incorpor
    0.96
    Act Density 2.071%

    No Known Activations