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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engineering
    -0.08
    levision
    -0.07
    एस
    -0.07
    ็บไซต
    -0.07
    ropa
    -0.07
     ศร
    -0.07
    eah
    -0.07
    .SpringApplication
    -0.06
    .activities
    -0.06
     ruth
    -0.06
    POSITIVE LOGITS
    ype
    0.06
    �
    0.06
    ww
    0.06
     Toy
    0.06
     injecting
    0.06
     mutually
    0.06
    گیر
    0.06
    Anime
    0.06
    ク
    0.06
    овор
    0.06
    Act Density 0.015%

    No Known Activations