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

    Neuronpedia

    INDEX
    Explanations

    cooking and preparation instructions in recipes

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

    Cooking steps/ingredients

    np_acts-logits-general · gemini-2.0-flash

    mixing and folding gently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.80
    égard
    -0.70
    UIAlert
    -0.64
     StatelessWidget
    -0.62
    unlike
    -0.61
    }?>
    -0.60
    ſelves
    -0.60
    argout
    -0.59
    =[];
    -0.59
    \}\\
    -0.58
    POSITIVE LOGITS
     until
    0.81
     gently
    0.78
     using
    0.72
     lightly
    0.71
     ensuring
    0.70
     asegur
    0.66
     carefully
    0.65
     then
    0.65
     vorsichtig
    0.64
     keeping
    0.64
    Act Density 0.450%

    No Known Activations