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

    Neuronpedia

    INDEX
    Explanations

    not equal to comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vairāk
    -0.82
     betreff
    -0.82
    venta
    -0.81
     Wię
    -0.81
    -0.79
     obtiene
    -0.77
     cilvē
    -0.77
     comenzar
    -0.77
    toContain
    -0.76
     creada
    -0.76
    POSITIVE LOGITS
     не
    1.10
     không
    1.07
     !=
    1.05
     diferen
    0.98
     not
    0.98
     habilit
    0.94
    )!=
    0.88
     ≠
    0.85
     !==
    0.83
    !=
    0.82
    Act Density 0.011%

    No Known Activations