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

    Neuronpedia

    INDEX
    Explanations

    a followed by noun or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ology
    0.61
    k
    0.61
    ici
    0.60
    icial
    0.60
    ik
    0.59
    лли
    0.59
    igned
    0.58
    icos
    0.55
    iding
    0.54
    ico
    0.54
    POSITIVE LOGITS
     angem
    0.58
    鞋
    0.57
    天使
    0.56
     دونك
    0.55
     GAL
    0.54
    病人
    0.53
     irritability
    0.53
     noirâtre
    0.52
    水印
    0.52
    香港
    0.51
    Act Density 0.001%

    No Known Activations