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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    毵
    -0.07
    ศาล
    -0.07
    emb
    -0.07
    ----------------------------------------------------------------------------
    -0.07
     triumph
    -0.07
    光辉
    -0.07
     yık
    -0.07
    .Encode
    -0.06
    只得
    -0.06
    zimmer
    -0.06
    POSITIVE LOGITS
    _mix
    0.08
    anas
    0.08
     dieta
    0.07
    ritic
    0.07
    ieties
    0.07
    tas
    0.07
    ialias
    0.07
    CREMENT
    0.07
    Ni
    0.07
    דיווח
    0.07
    Act Density 0.154%

    No Known Activations