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

    Neuronpedia

    INDEX
    Explanations

    handling hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溫度
    0.45
     veloce
    0.45
     レザー
    0.44
     bmw
    0.44
     furry
    0.44
    ინი
    0.42
    0.42
     lauren
    0.41
     believe
    0.40
     Believe
    0.40
    POSITIVE LOGITS
    es
    0.54
    o
    0.54
    v
    0.51
    u
    0.50
    as
    0.49
    q
    0.46
    á
    0.45
    amp
    0.45
    are
    0.43
    ad
    0.43
    Act Density 0.001%

    No Known Activations