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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vendors
    -0.07
     teacher
    -0.07
    护士
    -0.06
    .getElementById
    -0.06
     amounted
    -0.06
    Destroy
    -0.06
     consultant
    -0.06
    .setValue
    -0.06
    itational
    -0.06
     אפילו
    -0.06
    POSITIVE LOGITS
     OLD
    0.07
    omin
    0.07
     Kathleen
    0.07
    .delegate
    0.07
     עומ
    0.07
    AT
    0.06
     cre
    0.06
     bağlant
    0.06
    🔑
    0.06
    _OP
    0.06
    Act Density 0.101%

    No Known Activations