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

    Neuronpedia

    INDEX
    Explanations

    discount

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ısından
    -0.07
    �
    -0.07
     Top
    -0.06
    _branch
    -0.06
    ENT
    -0.06
    Detect
    -0.06
    BYTES
    -0.06
     iPhone
    -0.06
     headphone
    -0.06
     bom
    -0.06
    POSITIVE LOGITS
     prohibiting
    0.06
    ._
    0.06
    ोख
    0.06
     playbook
    0.06
     communicating
    0.06
     UserModel
    0.06
     chua
    0.06
    ...">↵
    0.06
     pageIndex
    0.06
    )...
    0.06
    Act Density 0.013%

    No Known Activations