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

    Neuronpedia

    INDEX
    Explanations

    expressions of emphasis or assurance in communication

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

    taking care to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menghadapi
    -0.44
     professora
    -0.44
     Ideen
    -0.43
     AppComponent
    -0.42
     ideen
    -0.42
     memenangkan
    -0.41
    geschoss
    -0.41
    SpringBootTest
    -0.41
     zagro
    -0.41
     čierna
    -0.41
    POSITIVE LOGITS
    特意
    0.58
     الرياضيه
    0.56
    UserScript
    0.51
    SerializeField
    0.50
    ArgsConstructor
    0.50
     ensured
    0.50
    RTHOOK
    0.50
    FXML
    0.48
     diligently
    0.48
     distanciation
    0.47
    Act Density 0.020%

    No Known Activations