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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following and adherence to ideas, practices, or models

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

    following instructions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }-*/;
    -0.53
    دانشنامهٔ
    -0.53
    bitField
    -0.47
    apimachinery
    -0.46
    SpringBootTest
    -0.46
     Administrativna
    -0.46
    testify
    -0.45
    InjectAttribute
    -0.45
    appspot
    -0.42
    MessageState
    -0.42
    POSITIVE LOGITS
     footsteps
    0.87
     guidelines
    0.69
     trail
    0.69
     instructions
    0.68
     instrucciones
    0.64
     logique
    0.63
     steps
    0.62
    guidelines
    0.62
     indicaciones
    0.59
     tradição
    0.59
    Act Density 0.043%

    No Known Activations