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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mas
    -0.08
     inbound
    -0.07
     форма
    -0.07
     Sith
    -0.07
    奴
    -0.07
    .deep
    -0.06
    aims
    -0.06
    _FR
    -0.06
     come
    -0.06
    .Emit
    -0.06
    POSITIVE LOGITS
    std
    0.07
    amily
    0.07
    NET
    0.06
    BIT
    0.06
    ileged
    0.06
     некоторых
    0.06
     소
    0.06
     algum
    0.06
     std
    0.06
    ahrungen
    0.06
    Act Density 0.042%

    No Known Activations