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

    Neuronpedia

    INDEX
    Explanations

    leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    త
    0.45
     टे
    0.44
     ដោយ
    0.41
    তনাম
    0.41
    spending
    0.41
    zech
    0.41
     mnoh
    0.41
     staggering
    0.41
    kowicz
    0.40
     has
    0.40
    POSITIVE LOGITS
    λλη
    0.46
    物体
    0.46
    ொண்டு
    0.45
    Lucy
    0.45
    луб
    0.43
     funcionalidad
    0.43
    ørte
    0.42
    が出
    0.42
     funzione
    0.41
     saudável
    0.40
    Act Density 0.005%

    No Known Activations