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

    Neuronpedia

    INDEX
    Explanations

    a specific, particular, different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Typical
    0.39
    ல
    0.36
     moderna
    0.36
    ittää
    0.35
     pai
    0.35
     Muchos
    0.34
     አመ
    0.34
    .~(\
    0.34
    inhas
    0.34
     Such
    0.34
    POSITIVE LOGITS
     specific
    1.04
     particular
    0.95
     específico
    0.89
    specific
    0.86
     특정
    0.83
     específicos
    0.81
    特定の
    0.81
     específica
    0.80
     different
    0.79
     spécifique
    0.77
    Act Density 0.027%

    No Known Activations