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

    Neuronpedia

    INDEX
    Explanations

    Fairness and shared costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    绽
    -0.08
    顶端
    -0.07
     bian
    -0.07
    .Dial
    -0.07
     DNC
    -0.07
     getDescription
    -0.07
    袒
    -0.07
     Jama
    -0.07
     rims
    -0.07
     Lawson
    -0.06
    POSITIVE LOGITS
    orption
    0.08
    .smart
    0.07
    บาง
    0.07
    Police
    0.07
    	await
    0.07
    蕲
    0.07
    >//
    0.07
    行李
    0.07
    pheres
    0.07
     условия
    0.07
    Act Density 0.040%

    No Known Activations