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

    Neuronpedia

    INDEX
    Explanations

    references to the operation or functioning of systems and devices

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

    how systems operate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.56
     numberWith
    -0.54
     Thal
    -0.54
     Candice
    -0.52
    allenges
    -0.50
    Thi
    -0.50
     annealing
    -0.50
    desertcart
    -0.50
    Goodbye
    -0.49
    TRAILING
    -0.49
    POSITIVE LOGITS
     operate
    1.50
     Operate
    1.45
     operates
    1.39
     operated
    1.38
     Operated
    1.31
    operated
    1.28
    Operate
    1.20
    operate
    1.16
     operar
    0.93
     Oper
    0.87
    Act Density 0.010%

    No Known Activations