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

    Neuronpedia

    INDEX
    Explanations

    location names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ats
    0.61
    ue
    0.61
    ini
    0.61
    <0x11>
    0.60
    ati
    0.60
    uer
    0.59
    
    0.57
    ilig
    0.57
    ation
    0.57
     세제곱
    0.56
    POSITIVE LOGITS
     Coastal
    0.82
     Bay
    0.80
     Riverside
    0.75
     San
    0.74
     Camp
    0.73
     Biblioteca
    0.73
     Lake
    0.72
     Mount
    0.71
     Willow
    0.70
     City
    0.70
    Act Density 0.164%

    No Known Activations