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

    Neuronpedia

    INDEX
    Explanations

    html script src

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াস
    0.71
    rmap
    0.59
    会
    0.59
     millionaire
    0.57
    ABLE
    0.57
    ্স
    0.57
    .
    0.56
    িন
    0.55
    ল্প
    0.55
    lação
    0.55
    POSITIVE LOGITS
    t
    0.84
    f
    0.60
     trachea
    0.58
     δυνα
    0.57
    tive
    0.57
     था
    0.55
    virk
    0.55
     تھے
    0.53
     있었
    0.53
    。[
    0.53
    Act Density 0.000%

    No Known Activations