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

    Neuronpedia

    INDEX
    Explanations

    health and related aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    2.23
    ש
    1.75
    还不
    1.70
    מ
    1.70
     restless
    1.67
    ки
    1.66
    ž
    1.63
    的情
    1.60
    вропей
    1.59
    ット
    1.55
    POSITIVE LOGITS
    ine
    1.84
    ية
    1.63
    fully
    1.62
    maintained
    1.59
     finanzi
    1.57
    PACT
    1.55
     найд
    1.55
    nw
    1.54
    setting
    1.52
    ir
    1.51
    Act Density 0.036%

    No Known Activations