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

    Neuronpedia

    INDEX
    Explanations

    conditions met

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     if
    -1.27
     fár
    -1.15
     chaleco
    -1.13
     that
    -1.08
     surtido
    -1.05
    いざ
    -1.05
     bocetos
    -1.03
    -1.03
     wenn
    -0.99
     דער
    -0.99
    POSITIVE LOGITS
     or
    1.16
     yaitu
    0.96
    itola
    0.92
     según
    0.92
     додат
    0.91
     конечно
    0.88
    Most
    0.87
     Throughout
    0.86
     While
    0.86
     provide
    0.85
    Act Density 0.046%

    No Known Activations