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

    Neuronpedia

    INDEX
    Explanations

    associated with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ний
    0.86
    ला
    0.84
    ?"
    0.82
    ?),
    0.79
    hearted
    0.78
     отвеча
    0.78
    可以说是
    0.77
    주고
    0.75
     ACHIE
    0.74
     Adventure
    0.72
    POSITIVE LOGITS
     roue
    1.15
     auxquelles
    1.15
     terjadinya
    1.13
     carrito
    1.10
     aman
    1.09
     grandi
    1.05
     teori
    1.05
     templo
    1.05
    erland
    1.05
     montagna
    1.03
    Act Density 0.005%

    No Known Activations