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

    Neuronpedia

    INDEX
    Explanations

    motor vehicles and bikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firmado
    0.42
    ジタル
    0.40
     modalités
    0.37
    ettamente
    0.37
    レポート
    0.37
    न्हें
    0.37
    مانی
    0.37
    惭
    0.37
     সুরে
    0.36
     📫
    0.36
    POSITIVE LOGITS
    ized
    0.81
    ised
    0.70
    bikes
    0.69
    cade
    0.67
    ola
    0.67
     scooter
    0.63
    boat
    0.59
    izada
    0.56
     scooters
    0.55
    ize
    0.55
    Act Density 0.006%

    No Known Activations