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

    Neuronpedia

    INDEX
    Explanations

    slippers, straps, snake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंत्रिकी
    0.47
     জেগে
    0.46
     pprint
    0.46
    ://$
    0.45
    वाहक
    0.44
    ]")]
    0.43
     cercano
    0.43
     pembang
    0.42
     ====
    0.42
    调查
    0.42
    POSITIVE LOGITS
    سي
    0.53
    at
    0.52
    on
    0.44
    Chel
    0.43
    ondere
    0.42
    inien
    0.42
    employer
    0.42
    en
    0.42
    فل
    0.42
    ون
    0.41
    Act Density 0.005%

    No Known Activations