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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     update
    -0.07
    /target
    -0.07
     desired
    -0.06
     free
    -0.06
    503
    -0.06
     freed
    -0.06
     royalty
    -0.06
     Proxy
    -0.06
    ultipart
    -0.06
     tear
    -0.06
    POSITIVE LOGITS
    xcd
    0.06
    Yii
    0.06
    .createUser
    0.06
     fiss
    0.06
     zdję
    0.06
     chef
    0.06
     exacerb
    0.06
    Exited
    0.06
     Challenge
    0.06
    |unique
    0.06
    Act Density 0.047%

    No Known Activations