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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acf
    -0.07
    郤
    -0.07
    𝓈
    -0.07
    Council
    -0.07
    ⅀
    -0.07
    一一
    -0.07
    /actions
    -0.06
     ]);↵
    -0.06
     alleles
    -0.06
     clever
    -0.06
    POSITIVE LOGITS
     hu
    0.08
    arda
    0.07
    したい
    0.07
     igual
    0.07
    欲しい
    0.07
    emic
    0.07
     Dok
    0.06
    omid
    0.06
    DebugEnabled
    0.06
     heure
    0.06
    Act Density 0.002%

    No Known Activations