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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ㉢
    -0.08
    עבד
    -0.08
     todd
    -0.08
    ᴖ
    -0.08
     граждан
    -0.08
    ولد
    -0.07
     מס
    -0.07
     وجه
    -0.07
    ぺ
    -0.07
    есп
    -0.07
    POSITIVE LOGITS
    防护
    0.07
    ת
    0.07
    _RELEASE
    0.07
    (),
    0.07
    Ρ
    0.06
    config
    0.06
    -storage
    0.06
    JUnit
    0.06
     catalog
    0.06
    tat
    0.06
    Act Density 0.004%

    No Known Activations