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

    Neuronpedia

    INDEX
    Explanations

    Software development tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     внутрен
    -0.06
    bread
    -0.06
    .src
    -0.06
     методи
    -0.06
    (players
    -0.06
    -sheet
    -0.06
     Dec
    -0.06
     takeover
    -0.06
    ooting
    -0.06
    (delegate
    -0.06
    POSITIVE LOGITS
    COORD
    0.07
    کن
    0.07
     BIO
    0.06
    莎
    0.06
    女性
    0.06
    bral
    0.06
    Accepted
    0.06
    JB
    0.06
     Status
    0.06
    Driven
    0.06
    Act Density 0.066%

    No Known Activations