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

    Neuronpedia

    INDEX
    Explanations

    financial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     パック
    -0.93
    ㄓ
    -0.88
     koruma
    -0.87
     scurt
    -0.84
    それは
    -0.82
     yavaş
    -0.81
    婳
    -0.81
     souffrance
    -0.81
    jandro
    -0.80
    thage
    -0.80
    POSITIVE LOGITS
     in
    1.02
    <th>
    0.89
    Encyklopedia
    0.85
     there
    0.84
    )।
    0.82
    ;
    0.80
    Сам
    0.79
     وجود
    0.79
    žin
    0.79
    blog
    0.77
    Act Density 0.101%

    No Known Activations