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

    Neuronpedia

    INDEX
    Explanations

    Seed germination and growth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WAY
    -0.07
    belum
    -0.07
     accountability
    -0.07
     drained
    -0.07
    vyšší
    -0.06
    evaluation
    -0.06
     yapılır
    -0.06
    jez
    -0.06
     accessor
    -0.06
    kir
    -0.06
    POSITIVE LOGITS
     ent
    0.07
     발
    0.07
    /class
    0.06
     송
    0.06
    =batch
    0.06
    .getcwd
    0.06
     велик
    0.06
    [slot
    0.06
     якому
    0.06
    调
    0.06
    Act Density 0.032%

    No Known Activations