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

    Neuronpedia

    INDEX
    Explanations

    service and resource management contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    bolded explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    1.57
    О
    1.38
     obiettivo
    1.37
    ות
    1.33
         
    1.27
     interno
    1.24
    -
    1.24
          
    1.18
     individuo
    1.17
     objetivos
    1.16
    POSITIVE LOGITS
    ان
    1.33
    in
    1.32
    f
    1.17
    G
    1.09
    hemm
    1.09
    he
    1.00
    ុ
    1.00
    hl
    1.00
    U
    1.00
    an
    0.98
    Act Density 0.079%

    No Known Activations