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

    Neuronpedia

    INDEX
    Explanations

    code, names, reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adventures
    -0.06
    eros
    -0.06
     худ
    -0.06
     guitar
    -0.06
     glo
    -0.06
     IS
    -0.06
    Stack
    -0.06
    =====
    -0.06
    )\↵
    -0.06
     ast
    -0.06
    POSITIVE LOGITS
     debated
    0.07
    (validate
    0.07
    економ
    0.07
    olulu
    0.06
    品
    0.06
    .WriteAll
    0.06
    -wife
    0.06
     згідно
    0.06
    (non
    0.06
    edio
    0.06
    Act Density 0.000%

    No Known Activations