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

    Neuronpedia

    INDEX
    Explanations

    questions about what or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     позволяют
    0.43
     možete
    0.42
    我们可以
    0.39
     můžete
    0.39
     може
    0.38
     могат
    0.38
     vimos
    0.38
     видим
    0.37
     possono
    0.37
     Puedes
    0.37
    POSITIVE LOGITS
     this
    0.45
     the
    0.41
     or
    0.41
     it
    0.40
     his
    0.38
    this
    0.37
     to
    0.36
     set
    0.34
     either
    0.34
     part
    0.33
    Act Density 0.123%

    No Known Activations