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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _dm
    -0.07
    Plain
    -0.07
    )(↵
    -0.07
     AFP
    -0.06
    (callback
    -0.06
    ][:
    -0.06
     Mastery
    -0.06
    Sie
    -0.06
    ：
    -0.06
    buyer
    -0.06
    POSITIVE LOGITS
     affiliated
    0.07
     جلس
    0.06
    _transition
    0.06
     ll
    0.06
     located
    0.06
     联
    0.06
     didFinish
    0.06
    	AND
    0.06
     mainAxisAlignment
    0.06
     March
    0.06
    Act Density 0.118%

    No Known Activations