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

    Neuronpedia

    INDEX
    Explanations

    steps in procedural text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timing
    -0.08
     MONTH
    -0.07
    �
    -0.07
     TYPE
    -0.07
     Timing
    -0.07
    次数
    -0.07
    许
    -0.07
     MANY
    -0.07
    TYPE
    -0.07
     ćete
    -0.07
    POSITIVE LOGITS
     waaronder
    0.08
     Meanwhile
    0.07
    бар
    0.07
     настоящее
    0.07
     compleet
    0.07
     آنلاین
    0.07
    gear
    0.07
     yox
    0.07
     stuff
    0.07
     Kartoff
    0.07
    Act Density 0.031%

    No Known Activations