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

    Neuronpedia

    INDEX
    Explanations

    code, errors, loading, empty states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mole
    -0.07
    .That
    -0.07
    Рµ
    -0.06
    Logs
    -0.06
    save
    -0.06
    ]));↵↵
    -0.06
    uarios
    -0.06
    	save
    -0.06
     leaves
    -0.06
    ble
    -0.06
    POSITIVE LOGITS
    SHOP
    0.06
     Israeli
    0.06
    _PRIORITY
    0.06
     AAC
    0.06
    يمي
    0.06
    .EventHandler
    0.06
    태
    0.06
    بط
    0.06
    salary
    0.06
     needle
    0.06
    Act Density 0.168%

    No Known Activations