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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noch
    0.39
     یخ
    0.39
    0
    0.39
    -
    0.38
    nodes
    0.37
    ad
    0.37
     soal
    0.36
    W
    0.36
    by
    0.35
     Sails
    0.35
    POSITIVE LOGITS
     virkelig
    0.39
     действительно
    0.38
    Gosudarstvennyj
    0.37
     என்பதற்கு
    0.37
     форми
    0.37
    μένα
    0.35
    하면서
    0.35
     என்றால்
    0.34
     即
    0.34
    ఎఫ్
    0.34
    Act Density 0.381%

    No Known Activations