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

    Neuronpedia

    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (operation
    -0.07
    /div
    -0.06
    Presenter
    -0.06
     Nội
    -0.06
     इल
    -0.06
     PROP
    -0.06
     renowned
    -0.06
    ード
    -0.06
     Mặt
    -0.06
     structure
    -0.06
    POSITIVE LOGITS
    GNU
    0.06
     bir
    0.06
    ory
    0.06
    irth
    0.06
    anned
    0.06
     transcription
    0.06
    _reason
    0.06
    çok
    0.06
     moins
    0.06
    _prom
    0.06
    Act Density 0.001%

    No Known Activations