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

    Neuronpedia

    INDEX
    Explanations

    offers features contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     implying
    1.11
     indicating
    0.92
     implication
    0.92
    indicating
    0.91
     imply
    0.88
     указыва
    0.85
     indication
    0.83
     Hinweis
    0.82
     pointing
    0.81
     मतलब
    0.80
    POSITIVE LOGITS
     contains
    1.65
     consists
    1.50
     boasts
    1.42
     features
    1.41
     depicts
    1.39
     combines
    1.38
     showcases
    1.37
     bevat
    1.36
     revolves
    1.33
     utilizes
    1.32
    Act Density 0.687%

    No Known Activations