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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	describe
    -0.08
    Probe
    -0.07
    𬬿
    -0.07
    Designer
    -0.06
     keyword
    -0.06
     promoter
    -0.06
    =""↵
    -0.06
    while
    -0.06
     suo
    -0.06
    Virtual
    -0.06
    POSITIVE LOGITS
     sailor
    0.08
    banana
    0.07
     ATH
    0.07
    天涯
    0.07
    栻
    0.07
    行驶
    0.07
    杉
    0.07
     McKay
    0.07
    whereIn
    0.07
     Tire
    0.07
    Act Density 0.001%

    No Known Activations