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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eden
    -0.08
    087
    -0.06
    价值
    -0.06
     его
    -0.06
     게
    -0.06
    nestjs
    -0.06
    intval
    -0.06
     vol
    -0.06
    .sqlite
    -0.06
    462
    -0.06
    POSITIVE LOGITS
    ucz
    0.07
    iều
    0.07
    ivity
    0.07
     candidacy
    0.07
    voucher
    0.06
    remember
    0.06
    pone
    0.06
     discredit
    0.06
     diret
    0.06
    ї
    0.06
    Act Density 0.160%

    No Known Activations