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

    Neuronpedia

    INDEX
    Explanations

    countries and US states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गणपति
    0.81
    Harvest
    0.79
    english
    0.77
    ósitos
    0.75
     ચૂક
    0.75
     tejto
    0.73
     aplikace
    0.72
    من
    0.72
    esters
    0.72
    BERGER
    0.71
    POSITIVE LOGITS
    UA
    0.64
     H
    0.58
     B
    0.57
    ు
    0.57
     take
    0.56
    দা
    0.56
     होऊ
    0.55
    rh
    0.54
     cope
    0.54
    ulina
    0.54
    Act Density 0.091%

    No Known Activations