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

    Neuronpedia

    INDEX
    Explanations

    Mixtral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    인이
    0.40
     silverware
    0.40
    راتكم
    0.39
    ıya
    0.39
    رز
    0.37
    अव
    0.37
    を一
    0.37
    peror
    0.37
    颍
    0.36
     പറ്റ
    0.36
    POSITIVE LOGITS
     mathvariant
    0.46
     Houd
    0.40
     NUE
    0.39
     lám
    0.39
    >
    0.38
     genau
    0.38
     P
    0.38
     Galois
    0.38
     mediator
    0.37
     deus
    0.36
    Act Density 0.000%

    No Known Activations