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

    Neuronpedia

    INDEX
    Explanations

    various forms of verbs or actions related to communication and introspection

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

    Japanese verb stems

    np_acts-logits-general · gemini-2.0-flash

    verb stem + auxiliary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fermés
    -0.62
     mijne
    -0.62
     fermeture
    -0.54
     opened
    -0.52
     barbati
    -0.52
    üyor
    -0.52
     closing
    -0.51
     berlaku
    -0.50
     fermée
    -0.50
     prisonniers
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.94
    ']))
    0.72
     referrerpolicy
    0.70
    )}</
    0.69
    )]:
    0.69
    ."</
    0.69
    })`
    0.67
    %"),
    0.67
    )}>
    0.67
    IntoConstraints
    0.67
    Act Density 0.112%

    No Known Activations