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

    Neuronpedia

    INDEX
    Explanations

    training and development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    malıdır
    -0.07
    (al
    -0.07
     начинает
    -0.07
    .hidden
    -0.06
    (stat
    -0.06
     unk
    -0.06
    (cors
    -0.06
    教授
    -0.06
    ┬
    -0.06
     صنع
    -0.06
    POSITIVE LOGITS
     Training
    0.07
    acobian
    0.07
     training
    0.07
    ETING
    0.07
     =↵
    0.06
     stationed
    0.06
    	valid
    0.06
     expertise
    0.06
     클래스
    0.06
    -&
    0.06
    Act Density 0.032%

    No Known Activations