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

    Neuronpedia

    INDEX
    Explanations

    express server setup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    沢山
    0.47
    izers
    0.45
    ))
    0.45
    Lots
    0.42
    astu
    0.42
    Similarly
    0.41
    Honestly
    0.41
    Nice
    0.41
     Lest
    0.41
    squares
    0.40
    POSITIVE LOGITS
     porta
    0.55
     complica
    0.47
    вича
    0.47
     consejo
    0.47
     prevenir
    0.46
     modernes
    0.46
     commissary
    0.46
     usuarios
    0.46
     moderna
    0.46
     conseiller
    0.45
    Act Density 0.005%

    No Known Activations