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

    Neuronpedia

    INDEX
    Explanations

    start of phase 1:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    like
    0.83
    idaire
    0.82
    type
    0.75
    such
    0.75
    y
    0.73
    size
    0.72
    ses
    0.71
    have
    0.70
    raises
    0.69
    haired
    0.69
    POSITIVE LOGITS
    :
    1.34
     Focus
    1.15
     Preparing
    1.15
     Practical
    1.13
    +:
    1.12
     Watercolor
    1.12
     Establishing
    1.12
     Preparation
    1.11
     Recharge
    1.09
     การ
    1.08
    Act Density 0.094%

    No Known Activations