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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rdf
    -0.07
    Budget
    -0.07
     проч
    -0.07
     convictions
    -0.06
     Legacy
    -0.06
    Reward
    -0.06
    interest
    -0.06
     diễn
    -0.06
     profile
    -0.06
     evaluation
    -0.06
    POSITIVE LOGITS
    WhiteSpace
    0.06
    )*
    0.06
    TG
    0.06
    WX
    0.06
     Mev
    0.06
    (serv
    0.06
    changer
    0.06
    DISABLE
    0.06
     `;↵
    0.06
    (shell
    0.06
    Act Density 0.008%

    No Known Activations