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

    Neuronpedia

    INDEX
    Explanations

    physical and emotional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administrativa
    0.48
     वैसे
    0.47
     subarray
    0.47
    相等
    0.47
     Negra
    0.47
    demir
    0.47
     गोरखपुर
    0.46
    鸪
    0.46
     alphanumeric
    0.46
     मैं
    0.45
    POSITIVE LOGITS
    "]:
    0.44
     BO
    0.42
     nature
    0.42
    urts
    0.42
    ла
    0.41
    ]:
    0.40
     large
    0.40
     foiled
    0.40
     air
    0.39
    բ
    0.39
    Act Density 0.000%

    No Known Activations