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

    Neuronpedia

    INDEX
    Explanations

    parentheses and plus signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Roy
    -0.07
     bets
    -0.07
     eldre
    -0.07
    qtt
    -0.07
    444
    -0.07
    ]]];↵
    -0.07
     방송
    -0.06
    Swagger
    -0.06
    Damage
    -0.06
     Bosnia
    -0.06
    POSITIVE LOGITS
    [unit
    0.06
     colum
    0.06
     इन
    0.06
    韩
    0.06
     prez
    0.06
     cons
    0.05
     کری
    0.05
     Kern
    0.05
     inplace
    0.05
     백
    0.05
    Act Density 0.103%

    No Known Activations