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

    Neuronpedia

    INDEX
    Explanations

    young professionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.54
     й
    0.51
     die
    0.51
     does
    0.48
    いつ
    0.47
     grows
    0.47
     dose
    0.47
    ows
    0.46
     is
    0.46
      
    0.45
    POSITIVE LOGITS
    <unused291>
    0.74
     पलीनोमियल
    0.74
     thisStudent
    0.73
     이런
    0.73
     oraș
    0.72
    <unused2060>
    0.72
    .??"]
    0.72
     navegación
    0.71
    <unused399>
    0.71
    <unused457>
    0.71
    Act Density 0.001%

    No Known Activations