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

    Neuronpedia

    INDEX
    Explanations

    package imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ari
    0.45
    пион
    0.43
    avam
    0.43
    成像
    0.43
    heiro
    0.42
     Comité
    0.42
     irmã
    0.41
    amesh
    0.41
     Gomes
    0.41
    aria
    0.40
    POSITIVE LOGITS
    ctxt
    0.42
     unreal
    0.40
     ustaw
    0.40
     базе
    0.38
    delivery
    0.37
     coff
    0.37
     faculties
    0.37
    glazed
    0.36
     intercept
    0.35
     এখন
    0.35
    Act Density 0.007%

    No Known Activations