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

    Neuronpedia

    INDEX
    Explanations

    references to secrecy and hidden governmental activities

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

    secretive government and transparency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StatelessWidget
    -0.64
    ніципалі
    -0.54
    IntoConstraints
    -0.49
    Sucesor
    -0.48
    lussen
    -0.47
     senhora
    -0.46
    Saluti
    -0.46
     Photocase
    -0.45
    skraft
    -0.45
     NSCoder
    -0.45
    POSITIVE LOGITS
     Transparency
    0.56
     transparency
    0.56
     secrecy
    0.55
     secret
    0.54
     transparence
    0.53
     covert
    0.51
    Transparency
    0.51
     hidden
    0.51
     secrets
    0.48
     openness
    0.47
    Act Density 0.228%

    No Known Activations