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

    Neuronpedia

    INDEX
    Explanations

    profession of faith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    業
    0.52
    дь
    0.50
    觀
    0.50
    มอ
    0.47
    ShaderType
    0.46
    ፈር
    0.45
    ား
    0.44
    يرو
    0.44
    тивна
    0.44
     Реа
    0.43
    POSITIVE LOGITS
    .
    0.58
    .”
    0.52
    ali
    0.52
    eras
    0.52
     exuber
    0.52
    !
    0.50
     erkl
    0.50
    -
    0.49
     succumb
    0.49
    iet
    0.48
    Act Density 0.000%

    No Known Activations