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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সৌন্দর্য
    0.58
    beauty
    0.57
     beauty
    0.56
     beleza
    0.52
     более
    0.52
    Beauty
    0.51
     Schönheit
    0.49
     সৌন্দর
    0.49
     Beauty
    0.48
     начин
    0.47
    POSITIVE LOGITS
     exactly
    0.53
     Done
    0.52
     done
    0.49
     height
    0.49
     precisely
    0.48
     exactamente
    0.47
    exactly
    0.47
     genau
    0.47
     exact
    0.46
    Exactly
    0.45
    Act Density 0.002%

    No Known Activations