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

    Neuronpedia

    INDEX
    Explanations

    terms related to the characterization and description of subjects or processes

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

    characterization of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.53
     <<<<<<<<<<<<<<
    -0.49
    ioutil
    -0.47
    
    -0.43
    WaitGroup
    -0.43
    
    -0.40
    längerung
    -0.39
    LayoutPanel
    -0.39
     aboli
    -0.39
     Hingga
    -0.38
    POSITIVE LOGITS
    character
    0.94
     characterizing
    0.87
     characterize
    0.86
     characterised
    0.86
     character
    0.85
     characterizes
    0.85
    Characterization
    0.83
     characterized
    0.82
     Character
    0.81
     CHARACTER
    0.81
    Act Density 0.018%

    No Known Activations