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

    Neuronpedia

    INDEX
    Explanations

    language specific qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Also
    0.46
    .
    0.45
    ;
    0.44
     -
    0.44
    .*
    0.43
     Then
    0.42
     (
    0.42
     Suppose
    0.41
     =
    0.41
    !
    0.41
    POSITIVE LOGITS
     procesos
    0.52
     proses
    0.49
     pitfalls
    0.49
     proceso
    0.48
     những
    0.48
     opciones
    0.48
     situaciones
    0.47
     nuances
    0.46
     processos
    0.46
     intricacies
    0.46
    Act Density 0.377%

    No Known Activations