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

    Neuronpedia

    INDEX
    Explanations

    code and debugging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corpses
    -0.07
    只能说
    -0.06
    ⊊
    -0.06
    ;color
    -0.06
     וח
    -0.06
    乩
    -0.06
    COMPLETE
    -0.06
    正文
    -0.06
    🄲
    -0.06
    jpg
    -0.06
    POSITIVE LOGITS
    Fetcher
    0.07
    Running
    0.07
    Nano
    0.07
     klein
    0.07
    /*
↵
    0.06
     Romania
    0.06
     warmth
    0.06
    -im
    0.06
    -------
    0.06
    Ram
    0.06
    Act Density 0.031%

    No Known Activations