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

    Neuronpedia

    INDEX
    Explanations

    West Ham

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demikian
    -0.84
     jiwa
    -0.84
    جستارهای
    -0.82
     PARSER
    -0.82
    برة
    -0.81
     таком
    -0.79
     shayari
    -0.78
    更何况
    -0.76
     ELSE
    -0.75
     framför
    -0.74
    POSITIVE LOGITS
     things
    0.96
    了一眼
    0.87
    HIT
    0.86
     really
    0.84
     traits
    0.79
     journalist
    0.78
     Paglinawan
    0.77
    聚
    0.77
    رایی
    0.77
     WTO
    0.77
    Act Density 0.005%

    No Known Activations