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

    Neuronpedia

    INDEX
    Explanations

    between and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    1.19
    rd
    1.03
    larıyla
    1.02
    ls
    0.95
    Discipl
    0.93
    a
    0.91
    le
    0.91
     spinoff
    0.89
     meticulous
    0.88
     blogging
    0.86
    POSITIVE LOGITS
     Valores
    1.12
     Strecke
    1.10
     između
    1.09
    éricos
    1.09
     valori
    1.07
     завжди
    1.05
     sliders
    1.04
     zwischen
    1.00
     apertura
    0.99
     posible
    0.99
    Act Density 1.340%

    No Known Activations