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

    Neuronpedia

    INDEX
    Explanations

    ++

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Β
    -0.07
    �
    -0.07
     Reward
    -0.07
    ازات
    -0.07
     svém
    -0.06
    ública
    -0.06
     Soph
    -0.06
     الداخ
    -0.06
     vår
    -0.06
    -arrow
    -0.06
    POSITIVE LOGITS
     și
    0.07
     harm
    0.07
    hardware
    0.06
    .response
    0.06
     ут
    0.06
    Enum
    0.06
    region
    0.06
     du
    0.06
    fine
    0.06
     yield
    0.06
    Act Density 0.007%

    No Known Activations