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

    Neuronpedia

    INDEX
    Explanations

    flexibility, comfort, clarity, look

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ábado
    0.76
    Request
    0.65
    iritual
    0.65
     dieser
    0.63
     হইয়৷
    0.61
     njemu
    0.60
    urgery
    0.59
     ਇਹ
    0.59
     tohoto
    0.59
    ProfileAction
    0.59
    POSITIVE LOGITS
     және
    0.63
     unparalleled
    0.62
     stabilit
    0.61
     efficiency
    0.61
     stability
    0.60
     flexibility
    0.60
     scalability
    0.60
     ballast
    0.60
     편리
    0.60
     weatherproof
    0.60
    Act Density 0.447%

    No Known Activations