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

    Neuronpedia

    INDEX
    Explanations

    final answer boxed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rand
    0.44
    캠
    0.40
    cery
    0.39
    isele
    0.39
     Coding
    0.38
    iboard
    0.38
    ब्रु
    0.38
     Preventing
    0.38
    Rand
    0.37
     Burma
    0.37
    POSITIVE LOGITS
     boxed
    0.46
    boxed
    0.44
     truncated
    0.40
     generan
    0.39
    워서
    0.37
    輸
    0.37
    reshold
    0.36
     गायक
    0.36
     generates
    0.36
    зит
    0.36
    Act Density 0.003%

    No Known Activations