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

    Neuronpedia

    INDEX
    Explanations

    Mistral AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keyup
    0.52
    free
    0.50
    {}",
    0.48
    fin
    0.48
    [];
    0.47
    ሉ።
    0.47
    but
    0.46
    clientId
    0.46
    [],
    0.46
    TERMIN
    0.46
    POSITIVE LOGITS
    是一個
    1.09
    是一个
    0.98
     provides
    0.95
     adalah
    0.95
     është
    0.94
     είναι
    0.92
     является
    0.89
    是一种
    0.89
     possède
    0.88
     biedt
    0.88
    Act Density 0.002%

    No Known Activations