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

    Neuronpedia

    INDEX
    Explanations

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loudly
    -0.07
    Sir
    -0.06
    currentUser
    -0.06
     defaultValue
    -0.06
     Yale
    -0.06
    ariant
    -0.06
     wallets
    -0.06
    Judge
    -0.06
     aliens
    -0.06
    ित
    -0.06
    POSITIVE LOGITS
     bew
    0.09
     ad
    0.07
    /github
    0.07
    (ad
    0.06
    depend
    0.06
    [${
    0.06
    (permission
    0.06
    (app
    0.06
    INDEX
    0.06
    ;};↵
    0.06
    Act Density 0.000%

    No Known Activations