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

    Neuronpedia

    INDEX
    Explanations

    Changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mü
    -0.07
     threats
    -0.06
    [block
    -0.06
     qualifying
    -0.06
     Tank
    -0.06
    뉴스
    -0.06
    вар
    -0.06
     multinational
    -0.06
    genic
    -0.06
    ξης
    -0.06
    POSITIVE LOGITS
    Concrete
    0.07
    =:
    0.07
     illeg
    0.06
     注
    0.06
    ved
    0.06
    側
    0.06
     matchmaking
    0.06
    .setLevel
    0.06
    อย
    0.06
    Conditional
    0.06
    Act Density 0.002%

    No Known Activations