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

    Neuronpedia

    INDEX
    Explanations

    toxicity score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ならでは
    0.44
     waterslide
    0.43
     Ash
    0.43
     Pale
    0.42
     prehistoric
    0.42
    yaj
    0.42
     Pressure
    0.40
     trees
    0.39
     Grain
    0.39
     Clearance
    0.39
    POSITIVE LOGITS
    同事
    0.39
    ရပ်
    0.37
    issent
    0.37
    Hib
    0.37
    詬
    0.37
    Scheme
    0.36
    小題
    0.36
    intention
    0.36
    ))}{
    0.35
    測定
    0.35
    Act Density 0.000%

    No Known Activations