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

    Neuronpedia

    INDEX
    Explanations

    your fork

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    goog
    0.86
     Nodo
    0.81
     nonconvex
    0.80
    🔗
    0.79
    w
    0.79
    WMN
    0.78
     OFW
    0.78
    +}^{
    0.77
    Escolh
    0.76
     괜
    0.75
    POSITIVE LOGITS
     হরি
    0.76
     benefits
    0.68
     Universities
    0.68
    вся
    0.67
     affects
    0.66
    ິງ
    0.66
     contracted
    0.65
     predicates
    0.65
     pipe
    0.64
     blazing
    0.64
    Act Density 0.001%

    No Known Activations