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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     `}↵
    -0.07
    _visit
    -0.07
     frowned
    -0.07
    .Fail
    -0.06
    �
    -0.06
     �
    -0.06
    _ep
    -0.06
    )"},↵
    -0.06
    〉
    -0.06
    _THIS
    -0.06
    POSITIVE LOGITS
     Bri
    0.07
     UITextView
    0.06
    Servers
    0.06
    /Framework
    0.06
     Linh
    0.06
     proceeding
    0.06
     inspector
    0.06
     Jaime
    0.06
    (reinterpret
    0.06
     федераль
    0.06
    Act Density 0.023%

    No Known Activations