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

    Neuronpedia

    INDEX
    Explanations

    specific domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.76
    ,
    0.70
    .
    0.65
    ;
    0.59
     menjalani
    0.55
    ando
    0.52
    ar
    0.52
    .?
    0.52
     suffisamment
    0.51
    ?
    0.51
    POSITIVE LOGITS
     it
    0.71
     this
    0.65
    ೃಹ
    0.65
    국
    0.64
     to
    0.64
    לי
    0.61
     ק
    0.61
    ק
    0.61
     י
    0.61
    ט
    0.60
    Act Density 0.410%

    No Known Activations