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

    Neuronpedia

    INDEX
    Explanations

    structured data or key-value pairs in a metadata format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JSON-like structures and code

    np_acts-logits-general · gemini-2.0-flash

    boolean values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varargin
    -0.60
    Portale
    -0.60
    <bos>
    -0.57
    varargin
    -0.41
    cze
    -0.41
     endforeach
    -0.41
    AddHtmlAttribute
    -0.40
     thủy
    -0.38
    
    -0.37
     rospy
    -0.37
    POSITIVE LOGITS
     true
    1.53
    true
    1.53
    false
    1.32
     false
    1.30
     True
    1.19
    True
    1.15
     TRUE
    1.12
    TRUE
    1.03
     False
    0.99
    False
    0.96
    Act Density 0.867%

    No Known Activations