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

    Neuronpedia

    INDEX
    Explanations

    RL

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    E
    1.01
    cam
    0.94
    ca
    0.85
     জানুয়ারি
    0.82
    backup
    0.82
     सीई
    0.82
    A
    0.81
    hc
    0.81
     cam
    0.80
    cal
    0.80
    POSITIVE LOGITS
    γραμμα
    0.79
     Furnace
    0.75
     Printable
    0.70
     médec
    0.70
     guérir
    0.67
    ляти
    0.67
    >);
    0.67
     potem
    0.67
    ických
    0.66
     descob
    0.66
    Act Density 0.001%

    No Known Activations