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

    Neuronpedia

    INDEX
    Explanations

    user instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zusätz
    0.53
    ett
    0.52
     olması
    0.52
     escalating
    0.52
     sigurn
    0.50
    îtier
    0.49
    ер
    0.49
     என்பது
    0.48
     intensifying
    0.48
     jeopard
    0.48
    POSITIVE LOGITS
    ，
    0.73
    g
    0.72
    u
    0.61
    a
    0.61
    an
    0.53
    t
    0.53
    y
    0.53
    v
    0.53
    ،
    0.52
    quakes
    0.50
    Act Density 0.125%

    No Known Activations