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

    Neuronpedia

    INDEX
    Explanations

    Completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _store
    -0.07
     rollers
    -0.07
     Hutch
    -0.06
    CriticalSection
    -0.06
    IMITIVE
    -0.06
    _front
    -0.06
    /qt
    -0.06
     shifting
    -0.06
    	level
    -0.06
    低
    -0.06
    POSITIVE LOGITS
     completed
    0.09
     completes
    0.08
     complete
    0.08
     completing
    0.07
    completed
    0.07
     completion
    0.07
     완
    0.07
     dokon
    0.07
    完成
    0.07
     termin
    0.07
    Act Density 0.039%

    No Known Activations