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

    Neuronpedia

    INDEX
    Explanations

    investment, app, reviewer, Educ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matched
    0.48
     Matches
    0.46
    匹配
    0.40
    ParentObject
    0.39
    uited
    0.38
     match
    0.38
     rég
    0.38
     アクセ
    0.38
    輙
    0.38
    atches
    0.38
    POSITIVE LOGITS
    Illegal
    0.41
    canonical
    0.41
    Canonical
    0.40
    FILENAME
    0.40
    kernels
    0.40
    UNIC
    0.39
     दुर्लभ
    0.39
    SSON
    0.37
    Sparse
    0.36
    Legal
    0.36
    Act Density 0.000%

    No Known Activations