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

    Neuronpedia

    INDEX
    Explanations

    foreign languages or special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quantas
    0.40
    ガ
    0.40
     გავ
    0.40
     reparations
    0.38
    扎
    0.37
     estudos
    0.37
     डाली
    0.36
     vors
    0.36
     அன்ன
    0.36
     doj
    0.35
    POSITIVE LOGITS
    IMAL
    0.43
    ပုံ
    0.42
    finement
    0.40
    様専用
    0.40
    “…
    0.40
    EXIT
    0.39
     Format
    0.38
    在這裡
    0.38
    ”…
    0.38
     इंपॉर्ट
    0.38
    Act Density 0.001%

    No Known Activations