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

    Neuronpedia

    INDEX
    Explanations

    references to control rooms and surveillance operations

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

    command and control center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.63
     transfieras
    -0.46
     Numerade
    -0.46
    tanleria
    -0.44
    PreferredItem
    -0.42
    IsMutable
    -0.42
     насељу
    -0.41
     condoms
    -0.40
    ewe
    -0.39
    piram
    -0.39
    POSITIVE LOGITS
     Control
    0.62
     control
    0.56
     monitor
    0.53
     Monitoring
    0.52
    Control
    0.52
     monitoring
    0.52
    
    0.49
    control
    0.49
     мони
    0.46
     Operators
    0.44
    Act Density 0.032%

    No Known Activations