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

    Neuronpedia

    INDEX
    Explanations

    Primary Batteries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redor
    0.86
    }~\
    0.86
    StatusCodes
    0.78
     conocer
    0.77
     Herrn
    0.77
     kwe
    0.77
     Samuel
    0.76
    抵达
    0.76
     Ges
    0.76
     grie
    0.76
    POSITIVE LOGITS
    a
    0.89
    tasks
    0.89
    theta
    0.84
    ex
    0.80
    om
    0.80
    raft
    0.80
    tools
    0.80
    ي
    0.79
    caption
    0.79
    range
    0.79
    Act Density 0.000%

    No Known Activations