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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोष
    -0.06
    _ME
    -0.06
    _books
    -0.06
     earlier
    -0.06
    adin
    -0.06
     cuffs
    -0.06
     infusion
    -0.06
    ǎ
    -0.06
     reign
    -0.06
    _FL
    -0.06
    POSITIVE LOGITS
     Denmark
    0.07
     Customer
    0.07
     ","
    0.07
    remote
    0.07
     thoughtful
    0.06
    Airport
    0.06
     Peru
    0.06
     intrigue
    0.06
    _percent
    0.06
     Remote
    0.06
    Act Density 0.026%

    No Known Activations