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

    Neuronpedia

    INDEX
    Explanations

    explaining or defining something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.44
     eine
    0.41
     een
    0.39
    对
    0.39
     analiza
    0.39
     uma
    0.38
     focuses
    0.38
     ఒక
    0.37
     encompasses
    0.37
     an
    0.36
    POSITIVE LOGITS
    rne
    0.32
    metallic
    0.31
    ymmetry
    0.30
    😐
    0.30
    mesini
    0.29
     ಭಾರ
    0.29
     நிலையத்தில்
    0.29
    seat
    0.28
     with
    0.28
     metallic
    0.28
    Act Density 0.030%

    No Known Activations