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

    Neuronpedia

    INDEX
    Explanations

    character descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indoctr
    0.49
     kaleidoscopic
    0.48
     Bauhaus
    0.43
     글로벌
    0.42
     plethora
    0.42
     meticulous
    0.42
     koncept
    0.41
     inú
    0.40
    produktion
    0.40
     grueling
    0.40
    POSITIVE LOGITS
     injured
    0.47
     messageShow
    0.46
     damaged
    0.45
    和
    0.43
     enfermedades
    0.42
    不同的
    0.42
     умень
    0.42
     разговари
    0.40
     impaired
    0.40
    颜色
    0.40
    Act Density 0.002%

    No Known Activations