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

    Neuronpedia

    INDEX
    Explanations

    Henry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     previstas
    1.01
     Uptown
    0.84
     abrasion
    0.83
     scrapes
    0.81
     spacers
    0.80
     covenants
    0.79
     asegur
    0.77
     invariants
    0.77
     inroads
    0.77
     routing
    0.76
    POSITIVE LOGITS
     blanchâtre
    0.88
     doute
    0.83
    '.$
    0.81
    iritto
    0.81
    दिग्ध
    0.80
     wounded
    0.80
    adinya
    0.79
    𝒆
    0.78
    idée
    0.77
     पौधा
    0.77
    Act Density 0.001%

    No Known Activations