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

    Neuronpedia

    INDEX
    Explanations

    Verb "to be" and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	version
    -0.07
    ody
    -0.06
    id
    -0.06
     steroids
    -0.06
    cord
    -0.06
    decorators
    -0.06
     parts
    -0.06
    chalk
    -0.06
    ο
    -0.06
    ork
    -0.06
    POSITIVE LOGITS
     mw
    0.07
    antee
    0.07
    分行
    0.07
    第二节
    0.07
    ਆ
    0.07
     Gün
    0.07
    channel
    0.07
     tunnel
    0.07
     מל
    0.06
    ΄
    0.06
    Act Density 0.108%

    No Known Activations