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

    Neuronpedia

    INDEX
    Explanations

    visualization and cultures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    磁盘
    0.42
    LastGen
    0.41
     Nawaz
    0.41
    ounter
    0.41
     sổ
    0.41
     रूट्स
    0.40
    沩
    0.40
     onClose
    0.40
     productColor
    0.40
    renzia
    0.40
    POSITIVE LOGITS
    in
    0.48
     depende
    0.47
    t
    0.47
     junt
    0.45
    attrib
    0.45
     substitu
    0.44
    1
    0.44
    ä
    0.43
     utiliser
    0.43
    he
    0.43
    Act Density 0.008%

    No Known Activations