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

    Neuronpedia

    INDEX
    Explanations

    welfare reform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mavros
    0.65
    உலகின்
    0.64
    çoivent
    0.64
    owę
    0.62
    вець
    0.62
     critérios
    0.59
    Ін
    0.58
     доступа
    0.57
    edik
    0.57
    ješ
    0.57
    POSITIVE LOGITS
    ).
    0.72
    。
    0.66
     )
    0.59
     S
    0.57
     F
    0.55
     are
    0.55
    )
    0.55
     (
    0.54
     hur
    0.52
    are
    0.50
    Act Density 0.001%

    No Known Activations