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

    Neuronpedia

    INDEX
    Explanations

    ph solution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corro
    0.39
    िस्थित
    0.39
     తయ
    0.38
     каждо
    0.37
     изо
    0.37
    酤
    0.37
     PAOK
    0.37
    ರುವುದು
    0.37
     ముఖ్య
    0.37
     తయారు
    0.37
    POSITIVE LOGITS
    SI
    0.40
    L
    0.39
     sk
    0.39
     SI
    0.38
     SE
    0.38
     SN
    0.38
    Syn
    0.37
    SN
    0.36
    Liv
    0.35
     Syn
    0.35
    Act Density 0.009%

    No Known Activations