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

    Neuronpedia

    INDEX
    Explanations

    words suggesting political or power structures

    oai_token-act-pair · gemini-2.0-flash

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]")]
    -0.88
    -0.83
     الرياضيه
    -0.82
     متعلقه
    -0.76
     AssemblyCompany
    -0.75
    ousand
    -0.72
    NewUrlParser
    -0.71
     onAnimation
    -0.70
     kaarangay
    -0.69
     betweenstory
    -0.69
    POSITIVE LOGITS
     State
    1.49
    state
    1.49
    State
    1.49
     state
    1.46
     STATE
    1.34
     states
    1.30
     States
    1.29
     Estado
    1.27
    STATE
    1.27
    States
    1.27
    Act Density 1.602%

    No Known Activations