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

    Neuronpedia

    INDEX
    Explanations

    explaining what or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ó
    0.42
    <strong>
    0.42
     hồ
    0.40
     thay
    0.40
     éviter
    0.40
     relo
    0.39
     sns
    0.38
     mov
    0.37
     օ
    0.37
    <b>
    0.37
    POSITIVE LOGITS
     Какие
    0.59
    Why
    0.58
    What
    0.57
    How
    0.55
    ۱
    0.55
    Mga
    0.54
    आइए
    0.52
    Какие
    0.51
    Reasons
    0.50
    Firstly
    0.49
    Act Density 0.067%

    No Known Activations