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

    Neuronpedia

    INDEX
    Explanations

    concerns about infections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他にも
    0.50
     পার্থক্য
    0.49
     as
    0.48
    τως
    0.48
     மிகவும்
    0.47
     އެ
    0.46
     reformas
    0.45
     socialist
    0.45
     outliers
    0.45
     leftist
    0.44
    POSITIVE LOGITS
    ette
    0.48
    르
    0.47
     GG
    0.46
     ذریعے
    0.44
    గ్
    0.43
     Manager
    0.42
    GG
    0.41
    Manager
    0.41
    RL
    0.41
    ذور
    0.41
    Act Density 0.000%

    No Known Activations