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

    Neuronpedia

    INDEX
    Explanations

    assertive actions and expressions of standing up for oneself or others

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

    stand up and fight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    couvrir
    -0.48
    tschaft
    -0.43
     financement
    -0.43
    ifikationer
    -0.40
    tanleria
    -0.40
     unknowns
    -0.38
     EnglishChoose
    -0.37
    큼
    -0.37
    tvguidetime
    -0.37
    améli
    -0.36
    POSITIVE LOGITS
     Brave
    0.56
    Brave
    0.55
     bold
    0.55
    brave
    0.55
    Stand
    0.53
     Bold
    0.53
     Stand
    0.52
     brave
    0.52
     BOLD
    0.50
    OGND
    0.50
    Act Density 0.035%

    No Known Activations