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

    Neuronpedia

    INDEX
    Explanations

    Best supporting actor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rumah
    0.78
    bicara
    0.76
    ać
    0.74
    mActivity
    0.73
    lifting
    0.73
     Pasal
    0.73
    eh
    0.72
    niveau
    0.72
    import
    0.72
    listing
    0.71
    POSITIVE LOGITS
    क
    0.91
     vários
    0.89
    ব
    0.88
     suboptimal
    0.84
     ट
    0.83
     threatening
    0.81
     διά
    0.80
     norepinephrine
    0.80
     máscara
    0.80
    ট
    0.80
    Act Density 0.000%

    No Known Activations