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

    Neuronpedia

    INDEX
    Explanations

    electronics boards

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emphasizes
    -0.08
     consisting
    -0.07
    Extensions
    -0.07
    _members
    -0.07
    PP
    -0.06
     natural
    -0.06
    exclusive
    -0.06
     served
    -0.06
    	id
    -0.06
     practices
    -0.06
    POSITIVE LOGITS
     //$
    0.06
     لا
    0.06
    *)(
    0.06
     ژ
    0.06
    endsWith
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    .IContainer
    0.06
    673
    0.06
     �
    0.06
    `"]↵
    0.06
    Act Density 0.028%

    No Known Activations