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

    Neuronpedia

    INDEX
    Explanations

    plus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Approved
    -0.07
    ADDING
    -0.06
     MutableLiveData
    -0.06
    Products
    -0.06
    Study
    -0.06
     Inputs
    -0.06
    maz
    -0.06
     Expected
    -0.06
    _router
    -0.06
    loc
    -0.06
    POSITIVE LOGITS
    (join
    0.07
     �
    0.06
     peuvent
    0.06
     comparable
    0.06
     fine
    0.06
    axy
    0.06
    ièrement
    0.06
     oblig
    0.06
    キング
    0.06
    ())).
    0.06
    Act Density 0.011%

    No Known Activations