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

    Neuronpedia

    INDEX
    Explanations

    redesign and redesigned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trouvent
    0.74
     utilisent
    0.73
     subcontractors
    0.70
     avaient
    0.69
     சமய
    0.69
     sporadic
    0.68
     innych
    0.67
     နောက်
    0.66
     tivesse
    0.66
     instalments
    0.66
    POSITIVE LOGITS
    (
    0.88
    g
    0.81
    3
    0.81
    <0x80>
    0.77
    ing
    0.75
    EL
    0.72
    V
    0.70
    ة
    0.68
    _
    0.67
    c
    0.66
    Act Density 0.000%

    No Known Activations