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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind created Google AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udges
    0.40
    痣
    0.36
     sess
    0.36
     presenters
    0.36
    实时
    0.35
     mapView
    0.35
     confirmations
    0.35
    ắm
    0.35
     আট
    0.35
     replies
    0.34
    POSITIVE LOGITS
     हमने
    0.43
    canic
    0.43
    willing
    0.43
     Tento
    0.42
     volonté
    0.42
     bewust
    0.42
     obwohl
    0.42
     وهذا
    0.41
     openness
    0.41
    utiliser
    0.41
    Act Density 0.001%

    No Known Activations