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

    Neuronpedia

    INDEX
    Explanations

    easier to remember or understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     m
    0.71
    1
    0.69
     M
    0.66
     converted
    0.66
     product
    0.65
     II
    0.65
     simulated
    0.65
    EM
    0.64
    0.64
     Brown
    0.63
    POSITIVE LOGITS
    orrag
    0.77
    addColorStop
    0.74
     énorme
    0.72
    <unused2177>
    0.71
    orgt
    0.71
    খ্যা
    0.71
     훨씬
    0.71
    dihydroxy
    0.70
     delicacy
    0.70
    usste
    0.70
    Act Density 0.000%

    No Known Activations