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

    Neuronpedia

    INDEX
    Explanations

    pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uldade
    0.71
    ረጥ
    0.69
     analogies
    0.68
    ționale
    0.64
    しば
    0.59
    illator
    0.58
     सीधी
    0.58
    ពេ
    0.58
     analogy
    0.57
     compound
    0.57
    POSITIVE LOGITS
     passing
    3.65
     pass
    3.45
    pass
    3.36
    passing
    3.31
     Passing
    3.29
    Pass
    3.16
    Passing
    3.16
     passes
    3.15
     Pass
    3.03
     passed
    2.86
    Act Density 0.159%

    No Known Activations