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

    Neuronpedia

    INDEX
    Explanations

    internal states and their context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datos
    0.93
    Idea
    0.92
    Knowledge
    0.87
    Tiene
    0.84
    yección
    0.84
    Cuenta
    0.84
     muestra
    0.83
    Logical
    0.82
    Study
    0.80
    muestra
    0.80
    POSITIVE LOGITS
     necessitating
    2.16
     hindering
    1.77
     requiring
    1.73
     causing
    1.65
     exacerbated
    1.57
     necessitate
    1.45
     forcing
    1.45
    导致
    1.43
     unresolved
    1.43
     despite
    1.43
    Act Density 0.302%

    No Known Activations