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

    Neuronpedia

    INDEX
    Explanations

    slf4j and Port Authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sla
    0.41
    င်
    0.40
    mba
    0.39
    Farmer
    0.38
    urul
    0.36
    insky
    0.36
    騨
    0.35
     Afr
    0.35
    ग्रीकल्चर
    0.35
    付けて
    0.35
    POSITIVE LOGITS
     TJ
    0.68
     pj
    0.68
    TJ
    0.63
     LJ
    0.59
     MJ
    0.59
     fj
    0.59
     SJ
    0.59
    UJ
    0.59
     Tj
    0.59
    LJ
    0.59
    Act Density 0.000%

    No Known Activations